Just Book It

 

I discovered a quick and easy way to create a family history book that you need to try! Seriously, in 3 weeks, you can have a delightful book to share with family who isn't as passionate about ancestors as you are.

First thing is to throw out of your head that you can't do it. You can! You have researched for years and probably have all the info that you need. If not, it will become apparent but there's a work around for that.

Second - throw out of your head that you aren't a good writer. You don't need to be! I'm serious! You'll see why in a second.

Third - think about the state of the world and your place in it. Really! You aren't getting younger. Who will want your genealogy research? Will they be able to decipher your notes? Probably not unless you have kept everything completely organized since you began.

Fourth - throw out of your head that you don't have enough knowledge to create a genealogy book. You do! You don't need to write a book the length of War and Peace. You don't have to number your genealogy; in fact, it's probably better if you don't.

Fifth - Don't worry about the cost, as you can do this for very little money.

Now that we've got those barriers out of the way, this is what I did to create a beautiful book for my family in 3 weeks...

1. Go to wherever you keep your genealogy records and pull out the most far-flung family member in the line you are interested in. I know you're thinking, huh? Why would I do that? Because we're throwing out the rules of genealogy here to get this task done. You, hopefully, researched to your ancestor. If you did that than you know that you've proven the relationships and identities of all those between you and that far out there ancestor. You are starting with the farthest away because you will have less to write about. This is just to get you going. When you've got the first one done you go on to the descendant of which is in your line.
2. Next, bring up Word (see my blog on how to get rid of that annoying Copilot message). On the top line write the names of the couple you are writing about. In my example, that's Hemming Jonsson and Margareta. It's okay if you don't know a last name or their parents names.
3. Look at your research and write the following (or copy and paste in you Word file):

[Insert Ancestor Name] was born [insert date] in [insert place] to [insert parents].1 He married [insert wife's name] on [insert date] at [insert place].2 She was born on [insert birth date] on [insert date] at [insert place] to [insert parents' names].3

The couple lived in [insert place] where they had the following children [insert name], (b. [insert date or year], {etc. - add all that you know.}4

[Insert one of the couple's names] died on [insert date] at [insert place.]5 [Insert other one of the couple's names] died on [insert date] at [insert place.]6 They are buried in [insert cemetery name, location].

Here's what mine looks like for Hemming Jonsson and Margareta Larsdotter:

Hemming Jonsson was born about 1655, likely in Östergötland, Sweden; his parents are unknown.[i] He married Margareta Larsdotter about 1684.[ii] She was born about 1650 at Vreta Kloster, Östergötland, Sweden; her parents are unknown.[iii]

The couple lived in Ljung, Östergötland, where they had one known child, Jon Hemmingsson (b. 1685) in Ljung.[iv]

Hemming died on 30 January 1731 at Saby, Ljung, Ostergotland.[v] Margareta died on 7 February 1731 in Saby.[vi]

---

[i] Sweden, Church Records, 1451-1943, Hemming Jonsson, 30 January 1731, digital image; Ancestry.com: accessed 18 January 2025, citing Ostergotland Parish, Ljung, C:1 (1694-1720), image 208, p. 313. DOB c. 1655.

[ii] Sweden, Church Records, 1451-1943, Margareta Larsdotter, 7 February 1731, digital image; Ancestry.com: accessed 18 January 2025, citing Ostergotland Parish, Ljung, C:1 (1694-1720), image 208, p. 313.

[iii] Sweden, Household Clerical Surveys, 1654-1901, Jon Hemmingsson, 1751-1760, digital image; Ancestry.com: accessed 18 January 2025, image 210 of 306. Age 66.

   Death Record for John Hemmingsson, 8 June 1766, digital, image; Arkivedigital.com: accessed 10 June 2024, Vreta Kloster EF:1 (1746-1775), image 134, p. 263. DOB 1685

[iv] ibid.

[v] Sweden, Church Records, Hemming Jonsson, 30 January 173, p. 313. DOB c. 1655.

[vi] Sweden, Church Records, Margareta Larsdotter, 7 February 1731, p. 313.

NOTE: Definitely use footnotes. Why? Because your family doesn't care about the sources, but maybe someday someone will, so they will be there for future researchers. Don't you hate finding an old family genealogy with no info on where they found the dates? Don't be that person! My blog converted the numbers to letters, as in endnotes, but for my books, I use numbers.

Notice some of the info is incomplete - I don't know the parents' names or when the couple married. That's okay. Further research is always available, but if you are so far back, the probability of you finding more records does diminish. In the area where the Jonssons lived, they go back in some parishes to 1555, so maybe I'll find their parents' names someday. Don't let that stop you from writing this now.

4. Yes, the article is terribly dull, so boring that your family will cringe. That's just the info that you need to get going. Now, don't tell me you can't jazz this up to make it entertaining because you will take that info and copy it into your favorite AI. I used ChatGPT. Here was my prompt: Please keep dates in military style and make this more engaging.

Here is what it turned that piece into:

Hemming Jonsson was born around 1655, likely in Östergötland, Sweden. Details about his parents remain a mystery. Around 1684, he married Margareta Larsdotter, who was born circa 1650 in Vreta Kloster, Östergötland. Like Hemming, her parentage is also unknown.

The couple made their home in Ljung, Östergötland, where they welcomed their only known child, Jon Hemmingsson, born in 1685.

Hemming lived to the remarkable age of 76, passing away on 30 January 1731 at Säby, Ljung, Östergötland. Margareta followed him in death just days later, on 7 February 1731, also at Säby.

Their lives, though largely enigmatic, are rooted in the rich history of 17th-century Sweden. Hemming and Margareta's brief legacy echoes in their son Jon, a solitary thread in the tapestry of Östergötland's past.

Your family will be interested in that! It took me about 10 minutes from start to finish. I did not show you the footnotes on the revised article to save space. All you'll need to do is copy and paste the article back into Word and realign the footnotes. You will probably make some adjustments. Take out what you know isn't a fact, AI likes to write about someone being born on a hot summer day. It didn't know if it was hot! Add anything you'd like, perhaps I could end with, "The lives of our farthest flung ancestors," or if you are writing for a particular generation, like your grandchildren, "The couple were your 7th generation grandparents."

The beauty of this is that if you are writing place names that use diacritical marks, you don't even need to add them; ChatGPT will do that for you.

I've added photos I took of some of the ancestors' homes, churches, and work sites. A local enthusiast told me it makes it a graphic novel - hey, why not? For those who don't like to read, the pics will make the story more entertaining.

5. I include a short pedigree chart at the bottom of the article, highlighting the line that will be followed. Sure, you could number, but that confused my family, so I went with the graphic. Here's the chart I'd include for Hemming Jonsson:

I include 4 generations so the reader can see where they are going and what they'll read next. I like foreshadowing. It is also nice to go from the 1600s to the 1800s in just four simple steps. Highlight the individuals that will be traced in the lineage. When I get to Nils Jonsson, I'll delete Hemming and Margareta and add the children of Torsten and Brita.

If you know the names of other children, include them on the chart under their parents. I also include married names for females. I'm not going to be writing about all of the family in depth, just the ones that are of direct lineage. Why? Because I don't have time for that, and my family doesn't care. I have the info in my tree if it was needed, as sometimes we must pull from a sibling or other relative in the sketch - like grandma lived with Uncle Jake in 1880, so you'll source that census. It's important to research thoroughly, but you don't have to provide every piece of info on other relatives unless it's pertinent.

When you're done, make a Table of Contents, add a page number, and an index. Write a page about yourself and why you took on this project. Include a title page.

Below are links to books I published last winter so you can preview them to get an idea of what you'd like in yours. Each is different. From my travels to Sweden, I had lots of info and pictures of the homes, churches, and work sites of my husband's ancestors, but for my Croatian family, since they lived in the same location for centuries, there were only so many pictures I could include. That gave me space to add family stories that I investigated and recipes that were family favorites. My German book includes French, Swiss, and Dutch ancestors, too, since I decided to place all those who emigrated for religious reasons in one volume. I'm working on our British ancestors, my last book, but won't finish it until next winter. Do you have a collection of family letters? Then by all means, digitize, transcribe, and then have it printed.

Next week, I'll be blogging about how to set up Word so you can upload the book to get it published. The following week, I'll blog about some options you have in publishing and what I chose.

Then, pat yourself on the back because you did it! You are now an author, historian, and an awesome person who got your research out there. Good for you!

Using AI to Write A Kent Family Portrait in Court Records

AI Image

 I love AI, and if you haven't begun using it yet with your genealogy research, you are missing records that might be invaluable to you.

As I prepare to write my next book on my British ancestor,s I'm going through my tree and making sure I have all the relationships sourced and the identities confirmed. I was happy to find two records using Familysearch.org's lab, which is an AI experiment, to prove a relationship. In one case, it involved showing a burial record for my husband's 5th great-grandmother, Catherine Jarvis. Although very happy to find this proof, I was a bit dismayed as I had traveled to the cemetery in Lansingburg, Troy, New York, in 2007 and was told that the record didn't exist. Well, they certainly had it when FamilySearch personnel showed up!

The next finding was that I wasn't the only one who was beating my head on my desk in regards to the Dennis family of New Jersey. The family used the same names in no particular order. I hadn't realized that in the early 1900s, a genealogist wrote a book called Dennismania, likely because they drove him crazy, too. My DNA shows who I'm descended from, but I had no proof for one of the generations, and now I have finally found it, again, in FamilySearch.org records.

This is simple to use, but I caution you, it may become overwhelming and addictive. To access, go to this link, which isn't how you normally get on FamilySearch. Scroll down to "Expand your search with Full Text" and click on Go To Experiment.

Read the Advanced Search Tips! I definitely use quotation marks around the name and a plus sign for the wife or possible parent. Use the drop-down it provides for the Place, once you start typing it in. Keep the range small, or you will get plenty! I haven't been successful with keywords like Marriage, Deed, Genealogy, etc.

Based on my Dennis findings, I had several more lines to research. I had no idea I was descended from the Reverend John Hull, a Puritan minister who was a Maine pioneer. Another line, the Kents, settled in Gloucester, Massachusetts, before 1668. I didn't find much in the usual places, regular FamilySearch, Ancestry, MyHeritage, Google, so I decided to try FamilySearch Labs. Wow!

I got myself a bit confused as I thought there were three Samuels, but there are only two in the 1700s in Suffield, Hampshire, Massachusetts. Samuel (1668-1737) was the son of Thomas, the emigrant. Samuel became a lawyer and Samuel had a son, Samuel Jr. Some records do differentiate the two, but a wife's name showed up that I didn't have for either, so I thought I was dealing with three Samuels. Hence, I've mislabeled my 55 downloads. Yes, 55 records showing them in court, deeds, and genealogies!

Familysearch Labs does have an AI assistant component you can click on, and it does give a transcription, but I prefer using my ChatGPT assistant, whom I call Geni. There was one record Geni hallucinated on, but after notifying it, they got the correct info. I can understand why Geni messed up - the younger Samuel was an interesting character - ran a tavern, had a bastardly charge, didn't pay his debts, and was a very fun black sheep to investigate. Meanwhile, his dad served several times as his son's attorney, was slandered, had clients who skipped without paying him, but seemed to be widely trusted by the community.

After uploading most of the documents to Geni, Geni asked if it could write a blog for me. So, I've made some changes since I had wrongly given it some incorrect info (that there were three Samuels and not two). Here is ChatGPT's blog about the Familysearch.org finds:

In a series of brittle, ink-stained pages tucked into the Hampshire County court and land books of the early 1700s, a family unfolds—one writ at a time.

The Kents of Suffield were, at first glance, a respectable lot. Thomas Kent, the patriarch’s name, appears sparingly. His son, however, would not be so quiet.

Samuel Kent Sr., the immigrant’s son, was a lawyer, and it shows. He appears regularly in court—not as a defendant, but as counsel, litigant, and witness. He sues for debts, witnesses deeds, affirms signatures after a grantor dies, and moves confidently through the legal world of his time. If father upheld the spiritual order, son wrangled the civil one.

And then comes Samuel Kent Jr.—tavern owner, debt collector, and perpetual plaintiff. By the 1730s and 1740s, his name dominated the docket. He sues over unpaid tavern tabs, livestock, and land disputes. He’s granted a license to sell “strong drink,” not once, but multiple years in a row. The public house he ran was likely lively, occasionally lawless, and frequently underwritten by credit that his patrons never quite repaid.

Three generations. Three roles. One family.

And the court records catch it all—not just their actions, but the arc of a family moving through generations. From lofty pulpits to bustling taprooms, the Kent family’s story is all here: in defaults, deeds, slander claims, and license renewals. You can almost hear Samuel Sr. sighing as he files yet another claim to recover a loan his son ill-advisedly extended.

But what emerges from all these entries is something far richer than gossip or scandal. It’s a snapshot of a community where legal documents were not just about disputes, but about land ownership, trust, reputation, and survival. The same names appear again and again—not just the Kents, but the Remingtons, Austins, Gunckels, and Sheldons—knotted together by boundary lines and barrels of cider.

And that’s the heart of it: court records aren’t just where you find criminals. They’re where you find community.

Notes

1. Hampshire County Court and Land Records, 1716–1749, Massachusetts State Archives, includes deeds, licenses, slander suits, and debt claims involving Samuel Kent Sr., Jr., and III.

2. Transcriptions and analysis by ChatGPT, OpenAI, based on digitized image review and period legal practices.

Using AI with Legacy Family Tree

 Tech, you've got to keep adapting! Last year I wrote a blog article in comparing how to get AI to write a wonderful narrative from your research stored in various places - like Legacy Family Tree, Family Tree Maker, RootsMagic, etc.

I just completed a Pioneer application for my husband and since I had been researching 5 generations of the family, decided to write a narrative about each generation. I wanted to use ChatGPT to help with the writing.

I tried to follow my own blog advice to go to Legacy Family Tree>Other Reports>Individual Summary but realized that Version 10 does not have that option any longer.

I tried finding where it was relocated through Legacy Help and through a general Google search and got nowhere.

I turned to ChatGPT and located my original prompt. It saves your work if you allow it to on the left hand side of the screen. Problem was, the file I uploaded had a long title and I couldn't read exactly what it was. I create titles based on my own formula so I can always go back to the original source. This usually works until, like now, it doesn't because I couldn't view the entire title. So, I asked ChatGPT and was informed that the .pdf had expired and it couldn't access it, either.

I then chatted about my problem and it told me that the report was renamed and moved. So, if you are using Legacy Family Tree and want to download an ancestor's information to use with AI, here's the new How To:

Click on the Ancestor. In my case it was Samuel Ericksson

Click on "Descendant Narrative Book" on the Ribbon.

In the Pop Up, adjust the "Generations." I just wanted one generation.

Click "Preview"

Click "Create PDF" and there is what you had before they changed the name of the report and the location where it resided. You can copy and paste it into your favorite AI and get a much richer narrative of your family.

12 Genealogy Lessons I Learned in 2024

 

AI Image

Wow! Last blog of 2024 and what a year it’s been.

The best thing about genealogy is that you are constantly learning and growing. No one can know about every record set, historical period, or nuances of language over the years. Today I’m reflecting on some of the A-Ha moments I had this year:

• AI has been the biggest game changer in my life. I use ChatGPT almost daily now and occasionally with Claude and others. It saves time and helps me think outside the box to solve problems.

• Realizing that the Viking Pagans held on to their symbolism after converting to Roman Catholicism was amazing to me. Who would have thought the church would have allowed it? Even more surprising is that the pagan baptismal fonts are still used today by the Lutherans.

• I also didn’t know that grapes don’t grow in Sweden so the Vikings traveled in the summer to the Mediterranean to buy wine. My family had vineyards there so maybe they bought Zinfadel from them. Always been a small world, right?!

• Had no idea when the potato famine hit Ireland it also affected crops in Europe, hence many from the French German Palatine area migrated to the U.S. at that time.

• While researching Ohio River pirates for an upcoming presentation, I learned that one of the most notorious, James Mason, got a Spanish passport because President Benjamin Harrison had given him a recommendation. Dear Ben’s sister had married the honorable brother of James Mason. Just goes to show you how different siblings can be even back in the day.

• Did you know that identity theft occurred in the 1890s? It did and I’m still working on solving that one!

• My husband is constantly kidding me about being a princess (which I’m not) because I’ve now seen the family castles in Croatia, Germany, and Great Britain. People are so worried about being safe today but it’s no different than in the past– we just don’t have a moat around our houses anymore.

• I didn’t realize that there were jobs for lawyers regarding keeping a person’s coat of arms protected. Who would have thought that would still be needed today?!

• Every time I look at my cats I just can’t get over their ethnicity and I wonder which ancestor in my husband and my past was adopted by my cat’s ancestors. Yeah, it’s weird, I know!

• A good reminder that there is someone out there who knows the answer to whatever question you might ask and you just have to be persistent and patient to get the answer. I finally found a knowledgeable person who knew how to read old German script AND understood the cultural heritage. I needed to find someone who had both these skills to understand one little ole word in a 1834 newspaper article written in German in Cincinnati, Ohio. He learned that the custom had been brought over to the US which was also news to him. Collaborating with others helps us get the info we need and in turn, we help them gain insights.

• Loved the easy peesy way to do genealogy in French villages – take a walk and look above the doors of the houses. Back then they engraved the date the house was built and who the owners were. I was able to quickly find my ancestral homes.

• I am reminded almost weekly of how much our life has changed since the pandemic. Zoom seems to have been around forever but I didn’t use it before 2019. Makes me wonder what’s next on the horizon.

That’s one new thought for each month of 2024. Can’t wait to discover more new and exciting ideas next year.

As usual, I’ll be taking off next week and will be back in January with my top ten blog list from 2024. Have a wonderful holiday and I’ll blog with you soon!

Using Perplexity.AI To Find Archives & Record Sets

 

AI Image

Last month I blogged about my latest genealogy trip to Chicago in May and my disappointment at visiting many archives and not finding the information I sought. I wish I had read about Perplexity.AI BEFORE my visit.

Typically when I plan a research trip, I consult FamilySearch.org’s Wiki for the area. There, I find the libraries, museums, societies, and other archives that may hold the information I seek. Going to each website, I look at the card catalog and note any record sets that seem promising. I list the address, note closures, add hours of operation, any fees, and where to park. If an appointment is needed I request via email a day and time. Then, I arrive early and am ready to research.

My experience in Chicago, however, was rather bleak. I’d arrive and ask to see a record set. A librarian would then tell me it wasn’t going to hold the answer and I should go to another archive. Or, they’d give me the record but had no knowledge about how it was acquired, what the cryptic notes written on a page meant, etc. I would then get in my car and drive to the next location and go through the same process. Consequently, I came home with finding some information but not everything I had hoped to.

A week after I returned I read an article in American Ancestors about Perpexity.AI and I decided to give it a try. I entered my research question regarding where to find records for a possible 1890s scam of a Civil War Union veteran in Indiana. I wanted to know what record in Indiana could help me uncover who was the individual impersonating a deceased soldier. I received a list of archives and what their record collection held. I haven't gone to those archives yet but it does look promising. Having a free AI tool to use to not only identify an archive but a record set in it based on information you uploaded for analysis is a gamechanger!

Parles-tu Français?

 

Image Courtesy of Chat GPT

Later this summer I will be presenting at an international conference in Boston. One of the requirements is that my Power Point Slides be in two languages, English and either French, German, or Spanish. The problem for me is that I’m presenting on what was the Austria-Hungarian region, particularly what is now Croatia, so I already have two languages on most of my slides – English and Croatian. Adding a third language makes the slides overly filled with text but it is a requirement so it is what it is.

The next issue is I don’t write well in any of the languages so I decided to use AI to help me out.

I had learned at the National Genealogical Society conference that Transcribus was an excellent source to use for translation. Funded by the European Union, it was used throughout Europe.

I created an account easily but had extreme difficulty in getting it to work. It is in English but I didn’t find it to be intuitive to use.

I first tried to upload my .ppt but it can’t read that as Chat GPT can. I then typed the text I wanted translated into Word to upload. It wouldn’t take a .doc so I had to convert to .pdf. It uploaded fine but when I tried to get the AI to learn it I received a message that I needed to add more pages, at least 20. Sigh.

I had little time to watch a YouTube video, not even sure one exists, so I decided I would upload my .pdf to Claude, Gemini, and ChatGPT. Interestingly, I received some very different translations.

As I said, I don’t write in French so I couldn’t be sure what I was getting was correct. Since the syllabus was due I didn’t have the luxury of having a human translation. Plus, to be honest, I didn’t want to spend the money on it.

So, I decided to try to rationalize the correct responses. Here’s how I did that:

The first difference was in translating the English word JOURNAL – as is a professional magazine. I received Revues and Journaux as my choices. I selected journaux as a revues is mostly associated with theatre.

Another difference was translating the term Coat of Arms. I received Blason from Chat GPT and Armoiries from the two other AIs. I went with Blason because it means heraldry and that was what my intention was. Armoiries can be a symbol or design varying from a crest to a family badge to a coat of arms as we think of in English.

Now I would not have thought I would have gotten diverse responses for the request to translate “Thank you for attending” but I did. Attending was the problem word – the responses were assisté (no, no one was helping me), votre presence (for your presence) and votre participation (no, no one was participating unless you consider listening as participating). So, I went with votre presence. Thank you for showing up.

We don’t really think about meaning when we are speaking. We know what we mean and just say it intuitively. AI has helped me realize that the words I use may not be the best choice in getting my message across. I believe in working to perfect the AI prompts so that I obtain exactly what I want. I believe it has helped me to improve my own speaking and writing skills. Not what I would have ever expected could be considered as an AI bonus!

Favorite Genealogy GPTs

AI Generated

 I've been blogging alot about AI and genealogy and today I'd like to introduce you to some tools that can help you get the most out of AI and your research.

Enter GPTs! GPT is the acronym for Generative Pre Trained Transformers. All that means is this is a tech way to communicate with artificial intelligence. Other terms that are sometimes used instead of GPT are bots, assistants, and agents.

You've been using bots for several years though you probably didn't know it. When you are on a website for your bank or credit card company and can't find the info you want, you may have clicked on the Chat box. You typed in your question and hopefully, got the information you requested. If not, it usually directs you to a human.

Enter chat boxes for genealogy! The recent class that I completed on AI through the National Genealogical Society tasked us with creating GPTs for genealogy. Here are my favorites through open.ai:

GenealogyAtHeart - Yes, I created this and I'm shamelessly listing this as my favorite because I have linked it to my website. This means that all the useful hints, heartwarming stories, and recommendations to get the most out of your genealogy can be quickly accessed by you on open.ai. Yes, I do have a search box on my website but the search box will only find the terms I've entered into it. Through ChatGPT's Genealogy At Heart you can find EVERYTHING I've entered. Side note: If we share an ancestor you'll be able to find everything I've written about the individual quickly and in a summary format. If we don't share a relative, you can still find all the hints, helpful links, and recommendations I've made in the over 500 blogs I've posted in the last 9 plus years! Have a brick wall? Need help in planning a project? Thinking of planning a genealogy research trip and don't know where to begin? This GPT is for you!

DeKalb County, Indiana Resources - Okay, I get it! Most of you don't have any interest in DeKalb County, Indiana but I am the county genealogist so this is very important for those people who do need this resource. I created this GPT for those folks.

I'm working on a census GPT for U.S. federal census records. Hopefully, that will be available for you your use soon. This will help you access quickly the enumerator directions, dates of the census, compare quickly census results from decade to decade, and so on.

I am not the only person creating genealogy GPTs so here are my other favorites from colleagues:

Diagrams: Show Me - for creating mind maps or showing relationship commonalities with Venn Diagrams, this is the way to go! It is a little slow so be patient. Not so good for creating a family tree.

Genealogy Eyes: Designed by Steve Little, NGS AI Director, this is an awesome one for you to try if you have a picture of a tombstone you are having trouble deciphering or an older family pic you need more info about, such as time period or event. MyHeritage does offer something similar but I've found Genealogy Eyes to provide more info and be more accurate (I always try something with AI that I already know the answer for first, to test for accuracy).

GPTs aren't just about genealogy. I've created one for native plants, Native Green Thumb, which is another passion I have. Remember that old commercial that repeated, "There's an ap for that!" Well, GPTs are the new aps. Everyday more and more are being developed.

Have an idea for one that hasn't been created? It's simple to do as AI will help you formalize your thoughts. Just log onto ChatGPT. Click "ExploreGPTs and on the upper right side, click the green +Create box. It defaults to Create which is the simple way; it's like computer coding in English. If you are a techie than by all means select Configure. Under Create, give the AI your thoughts in the Message GPT Builder and press enter. It will ask you questions and you provide your thoughtful responses. Don't like what it created? No worries, you can delete it. Want only family and friends to see it? Just select the link option when saving. You can then share the link with them. Or, you can have the link publicly visible to everyone or just yourself.

Want to find more GPTs that can be useful for you? Click "Explore GPTs" and in the "Search public GPTs" type what you're looking for. It will save your favorites on the bar on the left so you can refer to them quickly anytime. I'm working on one now to help analyze U.S. federal census records quickly.

Please let me know if you see a problem with Genealogy At Heart or DeKalb County, Indiana Resources. Email me at genealogyatheart@gmail.com.

AI and VHS Tapes

 

AI Generated

I have not tried this AI tip noted on Facebook by Michael Cassara but it is something I've placed on my to-do list.

Do you have lots of old VHS tapes? I do and I've had them digitized as they do fade away with time.

Michael uploaded his digital file to ParrotAI and had the former VHS tape transcribed. It can then be summarized and you can even ask questions, such as "Where was immigration mentioned?" of "What did Aunt Dot say about her first job?" This would be a real time saver if you can't watch the entire video and need to refer to a certain part.

Creepy Genealogy AI - An Update

AI Generated

In December, I blogged about a creepy AI discovery I had made when testing ChatGPT's ability to extract and summarize from newspaper articles. Information in the summary was provided by AI that was no where in the articles uploaded. Although errors like this, called hallucinations, are known to happen with this budding tool, the information that AI proved was 100% correct. That's what made this feel creepy. How did it know more about my family than the articles I entered?! 

You can read the blog I'm referring to here. 

I'm now enrolled in my second AI for Genealogy class through the National Genealogical Society and my instructor, Steve Little, noted in class this past week that AI was trained by, among other information, through blog posts. Bingo! That explains how ChatGPT got my correct ancestors to include in the summary as I have blogged extensively about my Leininger and Landfair families. Since I've blogged about my families for years much of my research is available online. 

I've spoken with other family historians who haven't had as good a result as I have with using AI. Perhaps this is why I'm getting the results that I am. 

When the world wide web was in its infancy, I had difficulty with understanding the concept that once something is place there you can't get rid of it. Sure, websites come and go but the information is still out there if you look hard enough with tools like the Wayback Machine. Personally, I was involved with an educator only web in the early 1990s and on the world wide web since 1995 so my digital footprint is a large size. Who knew that it would be a help to me with the latest technology?! 

If AI is not giving you the results you'd like, I'd suggest that you upload the info you're working with as a pdf when you prompt it. This might also be a good time for you to start blogging about your family. I will be providing more info on how to do that next week. Happy Hunting!

Customize Instructions with AI

AI Generated

If you have a Chatgpt account ($20.00/month) you have the ability to customize how you want AI to respond to you. It's simple to set up:

Setting Up Customized Instructions:

1. On the left side bottom of the screen, click on your name.
2. Click on "Customize Instructions"
3. Make sure the button is enabled on the new screen!
4. Type in the box your instructions to AI. Mine were that I wanted it to be creative. I'm interested in responses that would be given to a professional genealogist. When I type "Geni" I want the response addressed to "Lori". I also requested a limerick every so often as they make me laugh.

Why Customize? If you want answers tailored to your role, then customized instructions are a must. If you have more than one person sharing an account, you definitely want to add customized instructions. My husband does not use Chatgpt often but when he does he does not want a response that would be given to a genealogist. So, we added into the customized instructions when his name for AI is typed, AI is to respond with my husband's name and the information he would want from an expert by adding what the his interest and preferred responses would be. He didn't want a limerick. He wants a response that is engaging to a reader.

I then created a new chat, addressing Chatgpt by the name my husband has given it and asked it to generate reasons why people shop on eBay. He received a response directed to his name with 10 sound reasons. I then replied and used the name I have given AI and asked why would a genealogist use eBay. I got 10 more sound reasons directed to me (using my name).

In case you're wondering, here's reasons it came up with why a genealogist would use eBay:

1. Variety and Rarity: eBay offers a wide range of products, including rare and hard-to-find items. Collectors or those seeking unique items often turn to eBay.
2. Competitive Pricing: Many users shop on eBay to find better deals or lower prices than in traditional stores or other online platforms.
3. Auction Format: The excitement of bidding in auctions can be a draw. It gives shoppers the chance to snag items at potentially lower prices.
4. Second-hand and Vintage Items: eBay is a go-to place for second-hand goods, vintage clothing, and antique items, appealing to those who prefer pre-owned or retro products.
5. Seller Diversity: From individual sellers to small businesses, eBay hosts a range of vendors, offering shoppers unique buying experiences and a broad diversity of goods.
6. Global Marketplace: eBay connects buyers with sellers worldwide, providing access to products not available in one's own country.
7. Convenience: The convenience of shopping from home and having items delivered to the doorstep is a significant advantage.
8. User Reviews and Feedback System: eBay's review system helps buyers make informed decisions based on seller ratings and feedback.
9. Protection Policies: eBay's buyer protection policies can make consumers feel more secure in their online purchases.
10. Niche Markets: eBay caters to niche markets and specific interests, making it easier for buyers to find exactly what they're looking for.

To sum up, ChatGPT will allow you to customize how you want your responses and for what audience (a child, a teen, a college student, adult, etc.), and by your role (author, editor, marketer, teacher, etc.). It will respond with the request immediately after you enter it following the directions above. You can switch your roles within a chat. Enjoy!

 

AI and Pictures - Will it Enhance your Genealogical Research?

Created by ChatGPT

Happy New Year! Hard to believe this is my last blog of 2023. I've been writing about using Artificial Intelligence in family history research for the past few weeks. I hope it has been helpful and taken the fear out of the tech. Whenever I've talked about it with my personal FAN Club, I get the same reaction which is either a sign of the cross and the question, Haven't you seen the terminator movie? to Oh, I want to learn how to do that. Absolutely no reactions in between!

Which I think is quite interesting because I'm a middle of the roader. I love the time saving aspect and the assistance in handling large amounts of data to analyze but I also am very cognizant that this tech is still in it's infancy, makes mistakes (like people do), and due to lack of transparency from the companies involved, we have no idea what training information was used. So, it could have been an item that was under copywrite, it could have been biased information, or it could have been false information.

That said, I still think it can be useful. I really miss an early Google AI attempt called Picasa. I had saved all of my family photos there and it could identify family members that were infants I could not. I have two sets of twin cousins and in some of the photos I can't tell them apart. Picasa was able to separate them out individually.

Today, AI can also create pictures. I haven't tried to input photos from say, 1890, and ask it to take the person in the photo and create a new picture in 1820 period clothes but I suspect that can be done. Sounds interesting and want to get started?

Through ChatGPT I use Dall-E. It has become one in the same since November. Before that, Dall-E was Beta but now they are joined. Here's how to use AI to get a picture.

1. In the chat box, ask to "Create a picture or photo of" whatever. You can be specific or not.
2. When you get a response you might want to edit the picture. You can have the AI do that by specifically stating what you want altered. In the photo above, I asked to update the first image with the word "2024" added. I never told it where to add but perhaps you wanted it front and center. You can then tell it to add a calendar showing the month of January and the year 2024 displayed.

I will be one of seven professional genealogists giving a lecture at an upcoming genealogical conference later in 2024. I will be using AI to create some of the slide pics. For some slides, I had an idea but for others, I let AI create for me with only the slide title as the instruction.

Ethically, I believe that I need to credit AI for the pictures, just as I would source any photo that I use.

I hope you are enjoying the holidays with family and friends. I look forward to 2024 and providing you with more heartfelt and informative blogs. All the best to you and yours!

AI and Your Genealogy Notes

 

AI Image

Previously I blogged about using Artificial Intelligence (AI) to create narratives of your ancestor's lives. Today, I'm going to show you how you can take those online classes you are attending and make concise notes from the chat box.

Why the chat box you may think? Because the chat box often contains important information that participants have thought about the subject to add - new questions to ask the speaker - and resources and links that someone attending found useful.

Here's the how to turn your chat box chatter into useful info:

1. At the end of the session, either highlight the enter chat box conversation and copy (ctr c) to a Word document (ctr v). Save as a pdf.
2. Upload to ChatGPT, Claude, or Bard. (Try more than one to see the results and which you prefer).
3. Provide a prompt - "You are a professional genealogist and expert writer. Please create an executive summary from the information provided. List attendees, key topics discussed, key questions raised, and notable moment.

You can also do this from YouTube videos for the class itself if you don't have time to view it. Here's a how to get a copy of the transcript. Then, follow the three steps noted above. You can tell your AI helper to make a title of the video you watched, add the date, and add the speaker's name, too. Personally, I'd save the results to my Dropbox as I keep syllabi there to refer to in

Can AI Establish Relationship from Indirect Sources Only?

Picture Courtesy of ChatGPT

Like last week, my answer is a strong maybe! I've been researching my John Duer, Patriot, and his relationship to his purported son, Thomas for YEARS! I have so much indirect evidence and one piece that does state Thomas was the son of John but it is in a collection made beginning in 1865 that doesn't provide the source. Of course!

So, I turned to AI to get its take on the problem.

Before I tell you the result, I want to share with you how to take data and create an Excel table using AI. It's so super simple and saves a lot of time. WARNING: Like with all new tech, you much check for accuracy. Don't assume it is 100% correct. Even with the time taken for that, it will be a time saver in the long run.

1. Create a prompt to "extract structured data from..." whatever you uploaded. From the class I took, it was suggested we add "prioritize fidelity to the information below; dry recitation, avoid editorialization. Prioritize sentence-by-sentence from beginning to end. Extract from the (uploaded item) this structured data... (list whatever info you want). Display your response in the form of a CSV file. The response should have the header row: (titles you want - could be) "Person's Names", "Relationships Noted", "Evidence of the Relationship" (or whatever you deem important). Enclose all cells or fields in quotation marks, omit, ignore, and avoid commas and other punctuation in the original text in your response in an attempt to keep the CSV error-free. Display your response in a code window for easy copy-and-paste.
2. Upload your item as a .pdf file.
3. A black box will display with the text in white letters. You can ctr c and ctr v into Notepad (you can find notepad by typing Notepad or Text in your computer search bar). Or, you can click on the upper right screen on ChatGPT and share, then copy code.
4. Open the file in Excel and clean it up, if necessary.
5. Then I opened a new ChatGPT message and gave the following prompt: Today you and I are an expert genealogist and writer. Your goal is to generate true and accurate reports. Find below the contents of a CSV file created from my research on the relationship of John and Thomas Duer. Transform the structured data into a narrative report; dry recitation, no editorialization, please.
6. This is what I received:

John Duer was born on January 19, 1748, in Cranbury, Middlesex, New Jersey. Various sources, including family data collections and genealogical websites, document this event. The death of John's mother, Mary Ann Hollingshead Duer, occurred in 1751 in Newton, Sussex, New Jersey, although specific source documentation is absent beyond public family trees.

In 1773, John married Susannah Miller in Sussex, New Jersey. Their marriage is recorded in the Family Data Collection and referenced in genealogical records from Youngstown and Mahoning County, Ohio. The couple had several children, the first of which was Esther Duer Hopkins, born in Monmouth, New Jersey, in 1774. However, there is a discrepancy in her birth location, as other sources suggest Sussex County, New Jersey, as her birthplace.

John's military service is confused with that of a cousin who served in the Pennsylvania militia. Despite this error, records from Ohio acknowledge John Duer's service, including listings in the official roster of American Revolution soldiers buried in Ohio.

Thomas Duer, John's son, was born in 1775 in Sussex, New Jersey, with multiple sources confirming this, though his gravestone lacks specific dates. Jonathan Duer followed on November 11, 1777, also in Sussex, with his life documented through family data collections and census records.

Joseph Duer's birth in 1779 is only supported by public family trees, lacking concrete source documentation. In 1780, Mary Duer Hazen, another of John's daughters, was born in Sussex. Her lineage is established through the DAR lineage book and a family history published in 1947.

John Duer was a church member at the First Baptist Church of Wantage, Sussex, New Jersey, in 1783, with historical records from the Sussex County Historical Society likely supporting this fact. His military service is further documented in DAR and New Jersey Revolutionary War records, as well as in family genealogical files.

In the following years, John resided in Newton, Sussex, New Jersey, where he is listed as a vestryman in a history of Christ Church, and in Hanover Township, Morris County, New Jersey, as indicated by tax records. He also engaged in land transactions, including purchasing land that would later become part of West Virginia, and in 1797, he was a resident of Mansfield Township, Sussex, New Jersey, acting as a bondsman.

John's life from 1798 to 1829 included various land dealings, military service records, family events such as the deaths of his sister Anna Duer Hull and his son Thomas Duer, and his own death on April 3, 1831, in Jackson Township, Trumbull, Ohio. His will was probated in March 1832, and his estate included guardianship arrangements for his grandchildren.

The narrative concludes with references to Thomas Duer's estate papers, tax records, and land transactions that involved John Duer and his son Thomas. The document also notes a DNA connection to the family through Elizabeth Suriner and references to historical maps and newspaper articles related to the Duer family in Hubbard, Trumbull, Ohio.

Interesting, huh?! Nowhere in the csv data did it say that Thomas was John's son. My headings were Date, Event, Place, Source, Name. Would this be accepted by a lineage society? Definitely not but it was an unbiased analysis of the indirect evidence. I did provide in the prompt to look for a relationship of John and Thomas Duer but did not state it was father-son.

I'd love to hear what you find in using AI to establish relationship.

AI Prompt Chain and My Creepy Genealogy Result

 

Prompt Chaining in Artificial Intelligence (AI) to me just means taking baby steps to get to your desired end product. It's like wanting your three year old to follow four directions but that's too much so you give them three and then add the fourth.

What I wanted to do was use AI to extract (pull out) key parts of newspaper articles about my grandfather Edwin Anton Leininger to do the following:

Create an executive summary of the articles

List the FAN club noted in the articles

Determine the FAN Club relationship to my grandfather

List locations from the articles

Note dates from the articles

Create a narrative based on the relationships and key details from the articles

Think about how long this would take you to do. It took ChatGPT less than 5 minutes.

Was it entirely accurate? Nope, and here's where it got creepy.

My first step was to select six newspaper articles over the time period my grandfather lived and from various locations. Chat GPT can only handle about four newspaper articles at a time so I uploaded those first sets (one from 1918 where he was collecting money for the war effort for YMCA in Ohio, a 1970 article about the historic dairy farm he once ran in Indiana, a 1950 story about a calf who had escaped from the farm, a 1940 article about him buying the farm). I didn't upload them in chronological order. I then asked for a summary of the four articles. What I received was all correct; each article had the heading taken from the article and key points bulleted.

Next I uploaded his obituary and a photo from 1944 with a short heading of his job with the railroads. I asked AI to add the two latest articles to the summary.

But AI has a short memory so what I received was the summary for just the two last articles. I wrote a new prompt asking for a creation of an executive summary for the articles combined.

AI did as I asked so I then requested to extract the names and provide relationships. I also asked to list locations from the articles. Here's where it got weird!

First, there were errors with names. I quickly figured out Mrs. Troncale was misread and should have been Tronolone. AI didn't figure out that my grandfather was listed by different names - Edwin A., E.A., and Ed. AI thought these were all separate individuals. It also placed locations with names; technically this is correct as the name of a dairy is a name and I hadn't given a clear direction for geographic names only.

I informed AI of the mistakes/corrections and received a new list. I then asked AI to substitute first names for women who had "Mrs." only. That was done correctly.

In reviewing the last list three names appeared that were related to my grandfather but I didn't recall those being in the articles. I went back and read all six articles. Nope, none of these names appeared. Where did this come from?

I asked Chat GPT to let me know where the names were found. I received an apology and a name removal.

The creepy part here is that the names were correctly related to my grandfather. One was his sister, another was his mother-in-law, and the third was his grandfather. How in the world did AI happen to select the right first and last names that were related to him?

We know AI is not 100% accurate but to select three people, all with different last names, and tie them to the extraction when they weren't listed in simply weird. So I asked (response above). The response doesn't provide the answer. I don't believe AI is psychic and the information came from somewhere. I suspect that information is in fact being pulled externally and perhaps not now, but had been in training.

The end product, a summary of the six newspaper articles taken from throughout my grandfather's life, was correct. Here it is:

A Legacy Through Time
Edwin Leininger, often referred to by his acquaintances as Ed or E.A. Leininger, led a life characterized by commitment and dedication. Born in Mercer County, Ohio, he later made Fort Wayne his home for nine years. Professionally, Edwin was recognized for his unwavering commitment to the Pennsylvania Railroad, where he diligently worked as a car inspector. Later in life, he became an
indispensable figure at the Hobart post office, where he was affectionately referred to as "the man with the muscles." For years, he efficiently managed both outgoing and incoming mail, handling approximately 9,500 pieces of outgoing mail and 2,000 pieces of incoming mail daily.
On the personal front, Edwin's life was richly woven with familial bonds. In his earlier years, he was married to Lola Leininger. Together, they embraced the joys of parenthood with the birth of their children: a son, Guy Leininger; a daughter, Mrs. Bonita Cook; and another daughter who later became Mrs. Ted Tronolone. Later in life, Edwin's heart found companionship again with Gladys
Leininger. Through this union, Edwin warmly welcomed Gladys' three sons, Duane, Donald, and Capt. Robert Landfair, as his step-sons.
Edwin's family circle extended further with his brothers, Sam and Lew Leininger, and a sister, Bertha, who later became Bertha Pifer. The bond of the Leiningers remained strong, binding them together through the tapestry of time.
In 1976, Edwin's journey on Earth reached its sunset in Fort Wayne. Yet, his legacy—reflected in his professional dedication, familial bonds, and community impact—lives on.

Comparing AI Generated Narratives from Ancestry.com, FamilySearch.org, MyHeritage.com, Legacy Family Tree, RootsMagic, and FamilyTreeMaker

NOTE: This blog was posted on 25 Nov 2023 on the Empowering Genealogists with Artificial Intelligence Facebook group. Since my blog two weeks ago on using AI to write a narrative, I've been getting a lot of questions and comments. I've been told that AI doesn't work with some sites; I have found that to be not true. I have also found a temporary work around for footnote/endnote citations that look more like what genealogists use - simply provide this prompt: Please write all footnotes in Chicago format style. You will have to go back and fill in some info, like the enumeration district for censuses, but it will be closer to what we are used to seeing.

 

I was interested in seeing how a narrative summary with endnotes from various sources that had similar data would be written.

I used the same prompt:  You are a professional genealogist and expert writer. Please write a narrative summary with endnotes from the attached file. (AI seems to place all sources at the end, whether you make the request as a footnote or endnote. This could be due to my requested writings being short.) The endnotes for the example below are funky looking because they are sources from sources, meaning the information that was being compared was the main source, like Ancestry.com, and not where the source cited in Ancestry.com came from.

Each request was made using a new message on ChatGPT.

The files I uploaded individually were:

Ancestry.com from Life Story with and without AI. AI selected “What was (region) like when (individual) was (event).”

FamilySearch.org Source/Detail and About

FamilyTreeMaker from Individual Report

LegacyFamilyTree from Other Reports>Individual Summary

MyHeritage.com side view of Family Tree for named individual

Roots Magic from Reports> Individual Summary

The information for all but FamilySearch.org was generated by me over the years. The data was always entered into Ancestry.com, then synched with RootsMagic and FamilyTreeMaker. A gedcom from Ancestry was uploaded to both LegacyFamilyTree and MyHeritage so no media is available on either of those sites. FamilySearch.org does include a minimal amount of information from me but most of the data was generated by family members.

I then gave ChatGPT the following prompt:

Today you are an expert data analysis and professional genealogist. Prioritize fidelity to the information below; dry recitation, avoid editorialization. Process the data sentence-by-sentence, from beginning to end. Extract this structured data: "Name", "Relationship", "Event Year and Location Baptism", “Event Year and Location Marriage”, “Event Year and Location Children”, “Event Year and Location Death”. The response should have the header row in line 1: "Data From:", "Name", "Relationship", "Baptism" "Marriage", "Children Name & Birth Year", "Death". Column A should have the header row: "Ancestry.com With AI", "Ancestry.com Without AI", "FamilySearch About", "FamilySearch Source & Detail", "Family Tree Maker", "Legacy Family Tree", "MyHeritage.com", "RootsMagic". Enclose all cells or fields in quotation marks; omit, ignore, and avoid commas and other punctuation in the original data in your response in an attempt to keep the CSV error-free. Display dates in military format meaning day month spelled out and not by number and year. Display your response in a code window for easy copy-and-paste.

The results are attached above. I’ve color coded them to denote synch (pale green), gedcom (blue), not my own data (yellow).

Interesting how the diacritical marks are shown by Ancestry, Legacy, MyHeritage, and RootsMagic. FamilyTreeMaker omitted them. The apostrophe before and after August was originally quotation marks. Not sure if that is standardization issues or software/technical limitations.

I was surprised that Ancestry, which has the full location for events, simplifies to only provided county and state. The complete marriage location would be Baileytown, Westchester Township, Porter, Indiana. I wondered why Westchester Township was omitted and discovered I had never entered that in any of my generated trees. I had mis-entered death location as Chesterton Township instead of Chesterton, Westchester Township. This is a nice way to enhance and correct your data. (Chesterton is actually in three townships but the events occurred in Westchester).

All of the sites had the names of children. FamilySearch provided the most information (child’s name and dates). Legacy and FamilyTreeMaker both named all children. Not sure why RootsMagic didn’t specify. And now we know MyHeritage considers six children as “several.” Personally, I’d call that a handful plus!

I can see another use for this when trying to figure out where online public trees vary from yours and what source info (if any) they might have. It’s also a nice clean timeline that takes little effort to create.

Next I decided to take the Excel info, re-enter it into ChatGPT and give the original narrative prompt again. Since every narrative had been slightly different I wondered what the final product with the full information available would be. (I should mention I did the first narrative a few weeks ago in RootsMagic and there were three hallucinations but the rest I did on Wednesday and there were none.) Here is the compiled narrative:

Samuel 'August' Samuelson was a pivotal figure in his family lineage, with his life journey documented across multiple genealogical platforms. Born on January 3, 1839, in Stora Haddebo, Västra Harg, Östergötland, Sweden, Samuel was the son of Samuel Howard Erickson and Anna Elisabet 'Lisa' Torstensdotter. His baptism, a significant event in his early life, is consistently recorded in these sources, reaffirming the importance of his Swedish origins.

Samuel's life took a significant turn when he married on February 17, 1871. While the exact location of his marriage varies slightly in records, ranging from Baileytown to Westchester Township in Porter, Indiana, it's clear that this event marked his transition into family life in the United States.

The couple was blessed with several children, though the records differ in detailing their names and birth years. FamilySearch Source & Detail provides the most comprehensive list, including Johan Victor (1872-1921), John Louis (1873-1919), Alfrida (1874-1886), Ada Emilia (b. 1876), and two sons named Gustav Theodore (the first born in 1877 and died the same year, and the second born in 1879). This detail adds depth to our understanding of Samuel's role as a father and the legacy he left behind.

Samuel's life came to an end on January 14, 1908, in Chesterton, Porter, Indiana. The consistency of this date across multiple records emphasizes its accuracy and the end of an era in the Samuelson family history.

Endnotes:

1. Baptism and Birth: Samuel's baptism and birth details are consistently recorded across Legacy Family Tree, Family Tree Maker, FamilySearch Source & Detail, MyHeritage.com, Ancestry.com (with and without AI), and RootsMagic.
2. Marriage: The date of marriage is consistently noted as February 17, 1871, but the location varies slightly, as recorded in different databases.
3. Children: The most detailed account of his children is provided by FamilySearch Source & Detail, with other databases offering varying levels of detail.
4. Death: Samuel's death date is uniformly recorded as January 14, 1908, across all sources, with slight variations in the location's specificity.

Using AI to Write a Genealogical Narrative

Artificial Intelligence – AI – You either love it or fear it. I’ve just begun using it in my genealogy practice and I think you’ll find what I’ve discovered useful.

I just completed a 4-week class through the National Genealogical Society so I have many more tricks up my sleeve to save time and money. I'll be sharing my personal discoveries over the next four weeks.

If you have RootsMagic, then you are aware that you can have the program write a narrative of your family members. Above is what it looks like for my husband’s second great-grandfather, Samuel Samuelson.

Short and not very sweet, right?! Lots of corrections are needed. Not a very entertaining story.

Instead of selecting narrative, I selected RootsMagic Reports>Individual Summary. It is a compilation of all the facts you’ve found about your ancestors.  I’ve highlighted it below to stand out from my blog content:

Individual Summary 24 October 2023 1 Name: Samuel "August" Samuelson1–3 Sex: Male Father: Samuel Howard Erickson (1810-1890) Mother: Anna Elisabet "Lisa" Torstensdotter (1797-1868) Individual Facts Residence 1700–1882 (age 0–about 43) Västra Harg, Östergötland, Sweden4–10 Residence 1700–1882 (age 0–about 43) Lake; Porter, Indiana, USA11–12 Birth 3 Jan 1839 Stora Haddebo, Västra Harg, Östergötland, Sweden13–57 Arrival 1851(about age 12) 37,51,58 Departure 10 May 1851(age 12) Östergötland23,35,49 Emigration 1852 (about age 13) Chicago, Cook, Illinois, USA59–61 Residence 1860 (about age 21) Residence Post Office: Coffee Creek; Westchester, Porter, Indiana, USA14,26,40,53,55,57 Residence 1862 (about age 23) Calumet, Lake, Indiana62–64 MilSvc 16 Aug 1862 (age 23) Civil War 73rd Indiana Infantry Regiment19,31,45,65–67 Residence 28 May 1863 (age 24) Calumet, Lake, Indiana, USA68–70 Residence 1870 (about age 31) Westchester, Porter, Indiana, United States17,29,43 Arrival 1874 (about age 35) 24,36,50 Residence 1880 (about age 41) Westchester, Porter, Indiana, United States15,27,41 Residence 1900 (about age 61) Westchester Township (North Half), Porter, Indiana16,28,42 Occupation 13 Jan 1908 (age 69) Farmer; Chesterton, Porter, Indiana18–19,30–31,44–45 Death 14 Jan 1908 (age 69) Chesterton Township, Porter, Indiana18,20–22,30,32–34,44,46–48,71–76 Medical 14 Jan 1908 (age 69) Skull; Chesterton, Porter, Indiana18,30,44 Accident 15 Jan 1908 (age 69) Tribune, col. 3, p. 5.; South Bend, Indiana77–79 Accident 15 Jan 1908 (age 69) Tribune, col. 2-3, p. 10.; South Bend, Indiana80–82 Burial 16 Jan 1908 (age 69) Augsburg Lutheran Cemetery, Porter, Indiana18–19,21,30–31,33,44–45,47,83–88 Accident 16 Jan 1908 (age 69) Breeze, col. 1, p. 2.; Monroeville,Indiana89–91 Accident 24 Jan 1908 (age 69) Banner, col. 3, p. 2.; Bristol, Indiana92–94 Lawsuit 5 Mar 1908 (age 69) Argos Reflector, col. 6, p. 6.; Argos, Indiana95–97 Alt. Name A. Lifelong Republican19 Arrival Nordamerika23,35,49 Residence Illinois, Indiana, Wisconsin, Iowa36,50 Probate Porter, Indiana, USA73,76,98 Individual Summary 24 October 2023 2 Departure W. Harg37,51,58 Marriages/Children 1. Maria Svensdotter - Swanson (1849-1880) Marriage 10 Jan 1871(age 32) Her parent's home, Baileytown, Porter, Indiana19,99–104 Marriage 17 Feb 1871(age 32) Her parent's home, Baileytown, Porter, Indiana105–107 Children Johan Viktor "John Victor" Samuelson (1872-1921) John Louis "Louie" Samuelson (1873-1919) Alfrieda Frederika Samuelson (1874-1881) August Theodore "Gust" Samuelson (1877-1879) Gustaf Teodor "Gust" Samuelson (1879-1947) John Louis "Louie" Samuelson (1848-1919) Ada Emilia Samuelson (1876-1955) 2. Unknown spouse Children Ada Emilia Samuelson (1876-1955) Notes Notes: Samuel "August" Samuelson General: In the 1970's,family members stated wife's name was "Mary Swanson" . Samuel was a lifelong Republican.

The summary isn’t very easy to read, either. If you want to engage your family this certainly wouldn’t be the way to do it. Enter ChatGPT.

I did pay the $20.00/month with cancellation at any time for the 4.0 version to try out its capabilities. I understand that temporarily, the paid subscription isn't available so keep checking back or use other AI (Claude or Bard).

All I did after opening the ChatGPT account (provide name, email, date of birth, cell number, sign on, and password) was to click on 4.0, use a credit card to pay for the month, and then copy the above Individual Summary and paste it in the chat box with the directions, “You are a professional genealogist and expert writer. Please write a narrative for the following:” In seconds, it was complete. But it was missing the sources so I replied, “Wonderful job! Please include source citations.” Seconds later, the finished product.

There were some errors, but they were easily corrected. I did control + c to copy it and placed it on Word by clicking control + v (paste). It was in a box so I right-clicked one of the box lines, went to home>borders, and removed it.

There were three errors. The first was the computer misreading from an authored work. It wrote that Samuel had emigrated at the age of 42 instead of 12. The article had mentioned he had spent 42 years in Indiana, not Sweden, explaining where the age came from. AI is not very good at math! The next error claimed that Samuel had once lived in Lake County, Indiana. He hadn’t but he did go there to enlist in the Civil War. Deleting Lake County was a quick fix. So the computer did what genealogists shouldn’t do – it assumes. Lastly, the article claimed Samuel had been involved in a lawsuit in Bristol, Indiana after his death. Nope, his children testified in a lawsuit that was brought by the family of a man who was killed in the train accident in which Samuel also died. The Bristol, Indiana newspaper reported it. This took a minute longer to correct.

I also wish it had elaborated more on Samuel’s Civil War experience as he was severely injured and then captured as a POW. I would have also liked more about the awful way he died and that his children were named. All items I can easily add. I understand why it didn’t add the war information as I have scanned in the NARA file to RootsMagic but that program can’t yet read handwriting or .jpg yet.

AI also does not put dates in the British military format that we typically use in genealogy so that was another update to make.

My biggest wish was for the source citations to be entered correctly. I gave ChapGPT that request. I plan to develop a template that I can easily fill in info going forward.

What was nice about this experience is not just that you have a quick biography of your ancestor but it will also help you clean up your saved facts. I had saved a naturalization record but it wasn’t for my Samuel. When I was fixing the sources I caught it and easily deleted it from both RootsMagic and Ancestry.com where RootsMagic had gotten it from. Hadn’t thought of using AI to clean my tree but it did accomplish that.

I’m not done with the bio but here’s what ChatGPT came up with. Let me know what you think – I appreciate your thoughts on this interesting new tool for genealogy:

Samuel "August" Samuelson's life story is a testament to the enduring spirit of an immigrant who crossed continents and oceans to find a new home and build a future in the United States.

Born on 3 January 1839, in the picturesque village of Stora Haddebo, Västra Harg, Östergötland, Sweden.[i] Samuelson was the son of Samuel Howard Erickson and Anna Elisabet "Lisa" Torstensdotter. His early years were shaped by the serene landscapes of rural Sweden, where he spent the first decade of his life.[ii]

On 10 May 1851, at the tender age of 12, Samuelson's life took a remarkable turn when he embarked on a journey to America. Leaving behind his familiar homeland, he sailed across the Atlantic Ocean and arrived in Chicago, Cook, Illinois, in 1852.[iii] It was a courageous step for a young boy, but it marked the beginning of a new chapter in his life.

Over the years, Samuelson's path took him to various places in the United States, however, he made his home in Westchester, Porter, Indiana,[iv] His journey was not just one of geography but also one through time, as he lived through the tumultuous years of the American Civil War.

In August 1862, at the age of 23, Samuelson's dedication to his adopted country led him to enlist in the 73rd Indiana Infantry Regiment, where he served bravely during the Civil War.[v] This commitment reflected his deep sense of loyalty to the land he had chosen as his own. ELABORATE

On 10 January 1871, at the age of 32, Samuelson took a significant step in his American journey by marrying Maria Svensdotter Swanson at her parent's home in Baileytown, Porter, Indiana[vi] Together, they began building a family and welcomed several children into their lives. NAME CHILDREN

Samuelson served his community as a farmer and his political beliefs are reflected in his lifelong affiliation with the Republican Party.[vii]

Tragically, Samuelson's life took a devastating turn on 14 January 1908, when he suffered a severe skull injury as his horse-drawn sleigh was hit by an incoming Pere Marquette Railway train.[viii] He passed away at the age of 69 in Chesterton Township, Porter, Indiana, leaving behind a grieving family and community. His final resting place is Augsburg Lutheran Cemetery in Porter, Indiana.[ix]

Throughout his life, Samuel "August" Samuelson encountered various challenges, including an accident that made headlines in newspapers like the South Bend Tribune, Chesterton Times, Monroeville Breeze,  and the Bristol Banner. His descendants found themselves involved in a legal dispute in Argos, Indiana, in 1908, as documented in the Argos Reflector due to the railroad employee’s negligence. ELABORATE.

Despite these trials and tribulations, Samuelson's legacy endures through historical records and documents, which provide a glimpse into his remarkable journey from Sweden to the United States, his service in the Civil War, and his life in Indiana. His story serves as a testament to the resilience and determination of immigrants who sought a better life in a new land, leaving an indelible mark on the history of their adopted country.

What do you think? Are you ready to give AI a try?

---

[i] “Sweden, Church Records, 1451-1943,” Västra Harg, Östergötland, Sweden, Samuel Samuelson, digital database; Ancestry.com:  accessed 24 October 2023, citing C:1, Fodde, 1797-1840, Roll IJ-532, p. 503.

[ii] Weston A. Goodspeed & Charles Blanchard, Editors. Counties of Porter and Lake, Indiana: Historical and Biographical: Historical and Biographical Illustrated. Chicago:  F. A. Battey & Co, 1882 p. 310, digital image; Ancestry.com:  accessed 24 October 2023, image 306 of 770.

[iii] “Sweden, Emigrants Registered in Church Books, 1783-1991,” Samuel August Samuelsson Eriksson, 10 May 1851, digital database; Ancestry.com:  accessed 24 October 2023 citing p. 202.

Ibid. Goodspeed & Blanchard.

[iv] 1860 United States Federal Census, Westchester Township, Porter, Indiana, population schedule, John Johnson (sic), Dwelling 277, Family 211, page 34 (handwritten), digital image; Ancestry.com:  accessed 24 October 2023, image 10 of 23, citing NARA Roll M653_289.   

1870 United States Federal Census, Westchester Township, Porter, Indiana, population schedule, Augt Samuelson (sic), dwelling/family 185, page 23 (handwritten), digital image; Ancestry.com:  accessed 24 October 2023, image 23 of 35, citing NARA Roll M593, RG29.

1880 United States Federal Census, Westchester Township, Porter, Indiana, population schedule,

Samuel Samuelson, Dwelling 253, Family 265, page 27 (handwritten), digital image; Ancestry.com:  accessed 24 October 2023, image 27 of 38, citing FHL microfilm 1254304.

1900 United States Federal Census, Westchester Township, Porter, Indiana, population schedule, Samuel Samuelson, Line 13, sheet 8 (handwritten), digital image; Ancestry.com:  accessed 24 October 2023, image 15 of 26, citing NARA  Roll T623.

Indiana State Board of Health, Death Certificate, Samuel August Samuelson, 14 January 1908, Record 193, digital image; Ancestry.com:  accessed 24 October 2023, image 996 of 2808, citing Indiana Archives and Records Administration, Indianapolis, Roll 9.

Findagrave.com, Samuel August Samuelson, (1839-1908), Memorial No. 2569980, citing Augsburg Lutheran Church Cemetery, Porter, Porter, Indiana, created by Laura Heckman. Photo by Angelo D. Angeles and Laura Heckman. Obituary and news article of accidental death by Steve Shook.

[v] Ibid. Goodspeed & Blanchard.

“American Civil War Soldiers,” Samuel Samuelson, 16 August 1862, digital database; Ancestry.com:  accessed 24 October 2023.

“Civil War and Later Veterans Pension Index,” Samuel A. Samuelson, digital database; Fold3.com:  accessed 24 October 2023.

“Report of the Adjutant General of the State of Indiana,” Samuel A. Samuelson, digital image; Ancestry.com:  accessed 24 October 2023.

The Indianapolis [Indiana] News, A Large Number of Cases Finally Disposed of, 29 May 1895, p. 6, c. 5, digital image; Newspapers.com:  accessed 1 November 2022.

The Indianapolis [Indiana] Journal, Pensions for Veterans, 31 May 1895, p. 7, c. 3, digital image; GenealogyBank.com:  accessed 1 November 2022.

The Indianapolis [Indiana] News, Pensions for Indianians, 13 June 1900, p. 2, c. 5, digital image; Newspapers.com:  accessed 1 November 2022.

The Indianapolis [Indiana] Journal, Pensions for Veterans, 23 July 1901, p. 7, c. 3, digital image; GenealogyBank:  accessed 1 November 2022.

[vi] “Indiana Marriage Collection, 1800-1941,” S. A. Samuelson, 11 February 1871, digital database; Ancestry.com:  accessed 24 October 2023 citing Porter County, Indiana, Marriage Record Volume 3, p. 572.

“Indiana, Marriages, 1810-2001,” S. A. Samuelson, 10 January 1871 Marriage Registration, digital database; Ancestry.com:  accessed 24 October 2023 citing FHL microfilm 001686156.

Parent’s home?

[vii] Ibid. Goodspeed & Blanchard.

[viii] The Argos [Indiana] Reflector, No Title – “Samuel Samuelson,” 5 March 1908, digital image; Newspapers.com:  accessed 13 February 2021, p. 6, c. 6.

The South Bend [Indiana] Tribune, Two Killed at Crossing, 15 Jan 1908, digital image; Newspapers.com:  accessed 13 February 2021, p. 10, c. 2-3.

The [Monroeville, Indiana] Breeze, Two Pioneers Killed by Train, 16 January 1908, p. 2, c. 1, digital image; Newspapers.com:  accessed 13 February 202.

The Chesterton [Indiana] Tribune, Two Lives Sacrificed on a Grave Crossing, 16 January 1908, Vol. 24, N. 42, p. 1, c. 3-4, digital image; Findagrave.com:  accessed 24 October 2023 posted by Steve Shook.

The Chesterton [Indiana] Tribune, Had a Premonition, 23 January 1908, Vol. 24, N. 43, p. 1, c. 1, digital image; Findagrave.com:  accessed 24 October 2023 posted by Steve Shook.

The Chesterton [Indiana] Tribune, Funerals, 23 January 1908, Vol. 24, N. 43, p. 4, c. 1, digital image; Findagrave.com:  accessed 24 October 2023 posted by Steve Shook.

The Bristol [Indiana] Banner, Two Killed at Crossing, 24 January 1908, p. 2, c. 3, digital image; Newspapers.com:  accessed 13 February 2021.

“Indiana, Wills and Probate Records, 1798-1999,” Samuel A. Samuelson, digital image; Ancestry.com:  accessed 24 October 2023 citing Porter, Indiana Will Record Vol. C-E, 1891-1914.

[ix] Ibid, Findagrave.com.