Louis Kessler’s Behold Blog

A few years ago, the Association of Professional Genealogists  @APGgenealogy started requiring that members report at least 12 hours of Continuing Education each year. I found the task of listing my CE time quite interesting and have posted them each year.

Below is my Continuing Education activity list for 2024. Each event was 1 hour unless otherwise noted.

Webinars – Total 28 hours

• Jan 3 – Artificial Intelligence and Genealogy: New Beginnings in 2024 – Steve Little, Legacy Family Tree Webinars
• Jan 17 – Resolving Conflicting Birthdates and DNA Painter – Lisa Cooke, Genealogy Gems Podcast (30 min)
• Feb 13 – MyHeritage Knowledge Base – James Tanner, Family Tree Webinars
• Feb 13 – Meet MyHeritage’s Global Experts – Daniel Horowitz, FamilySearch Facebook Live
• Feb 14 – AI and Genealogy – Thomas MacEntee, Family Tree Webinars
• Feb 21 – Genealogy Smart Start – Elizabeth Gomoll, Family Tree Webinars
• Feb 26 – Learn how to create a digital genealogy workflow. Janine Adams – MyHeritage Live from Mar 30, 2023.
• Mar 17 – Sorting Your DNA Match Lists - Kelli Bergheimer, webinar for the Allen County Public Library
• Mar 20 – 7 Tips for Using AI as Your Genealogy Assistant – Dana Leeds, Family Tree Webinars
• Mar 22 – Finding the Generation of Connection – Diahan Southard – Your DNA Guide
• Apr 9 – Ask the Experts with Genetic Genealogist “The DNA Geek” Leah Larkin – Diahan Southard, Your DNA Guide (30 min)
• Apr 11 - A Guide to Cemetery Photography – Judy Russell, Family Tree Webiinars.
• Apr 12 – 6 Tips to Build a Family Tree for Busy People – Tara Shymanski, Family Tree Webinars
• Apr 26 – DNA for Genealogy – An Evolving Journey – Jennifer Zinck, Association for Professional Genealogists (90 minutes)
• May 1 – Strategies to Analyze Endogamous DNA – Alec Ferretti, Family Tree Webinars
• May 5 – Advance Your Jewish Research in the Former Russian Empire with Important Online Resources and Strategies – Joe Everett - Santa Cruz Jewish Genealogy Society (120 min)
• May 22 – A Tour of Goldie May’s Genealogy Power Tools – Richard Miller – Legacy Family Tree Webinars
• June 6 – Using AI to Analyze and Visualize Your Census Data – Dana Leeds – YouTube (20 min)
• July 9 – 10 Reasons Why MyHeritage is a Genealogist’s Best Friend – Melissa Barker, Family Tree Webinars
• Aug 8 – Preparing for 3rd Party DNA Tools by Sara Cochran – Virtual Genealogical Association (Live presentation was June 30)
• Sep 18 – Practical Chromosome Mapping: Gaining Insights from Segments of DNA – Jonny Perl, Family Tree Webinars
• Oct 19 – Rubik’s Cube Genealogy: A New Twist on Your Old Data – Elissa Scalise Powell, Family Tree Webinars
• Oct 19 – Keeping Track of Surnames – Fiona Brooker, Family Tree Webinars (20 min)
• Nov 12 – Turn Your MyHeritage Record Matches into a Research Roadmap – Lisa Alzo, Family Tree Webinars
• Nov 20 – Top Ten AI Genealogy Breakthroughs of 2024 – Steve Little, Family Tree Webinars (90 min)
• Nov 22 – Information Overload? Effective Project Planning, Research, Data Management & Analysis – Elizabeth Shown Mills, Family Tree Webinars (80 min)
• Dec 4 – Challenging Some DNA Myths: Learn to Separate DNA Fact from Fiction – Paula Williams, Family Tree Webinars (80 min)
• Dec 17 – I (Think I) Have a DNA Network: Now What? - Diahan Southard, Family Tree Webinars

Conferences (Online) – Total 13 hours

1. Feb 29 to Mar 2 – RootsTech 2024
• Genetic Genealogy Turns 25: DNA Experts Tell Their Stories – Diahan Southard
• What’s New at Ancestry in 2024 – Crista Cowan
• The Knowles Collection: What Is It and How Do I Use It – W. Todd Knowles (30 min)
• Drowning in Family Photos: Why Metadata Makes Your Library Searchable and Enjoyable – Rich Harrington
• U.S. Synagogue Records as Genealogical Resources – Ellen Kowitt
• Using FamilySearch for Jewish Research – W. Todd Knowles
• FamilySearch GEDCOM 7: Popularity, Resources and Future – Gordon Clarke (30 min)
• Syncing AQ/PAF data with Family Tree (3 videos) – Gaylon Findlay, Ancestral Quest
• What’s in a name? DNA, surnames and one-name studies – Debbie Kennett
2. Nov 1 to Nov 3 – WikiTree Symposium 2024
• Creating an Ancestor Sketch – Thomas MacEntee
• Finding the records for “impossible” genealogy. Lessons learned from a Chinese genealogist – Linda Yip
• Hopping Down the Paper Trail – Sara Cochran
• Using AI in Family History Research – Melanie McComb
• From Name Collection to Name Confirmation: Adding Leaves tot he RIght Branch – Cheri Hudson Passey

In total, my time in 2024 was 41 hours. By comparison, 2023 was 39.5 hours and 2022 was 38 hours.

I’m working hard on Behold to get Version 0.99.1 Beta released. It will include GEDCOM export which I think will make it a valuable tool for many genealogists.

It has been taking longer to finish the GEDCOM export than I had hoped, partly because of opportunities to work on my own genealogy (which I don’t apologise for), but also because of a change needed to Behold to get the export to work. That change being to not repair the GEDCOM when it is input. Instead it must leave it as it is so that it can be exported back out again as input if the user desires it that way. The repair instead should take place when Behold displays the data in its Everything Report, or when the user decides to export following the GEDCOM 5.5.1 standard.

But that’s not the topic of this article. I’d like to present a typical programming mystery of the type that I often encounter, and a typical methodology I use to see my way through it.

Like a Mystery Novel

My wife loves a good mystery novel. It gets her thinking. You have to be observant to pick up the clues as some lead you in the right direction and others take you on a wild goose chase. When the novel ends, you can be self-satisfied if you figured out who-dunnit before the answer is revealed, or you can be surprised or shocked when you didn’t get it. A good mystery novel is something you will enjoy if the story was interesting, the premise of the mystery was unusual but made sense, and the solution in the end was plausible.

As a genealogist, something always creeps up that doesn’t make sense. Why is the father only 15 years older than the child. Was the family really in Ohio one year, Massachusetts the next, and back in Ohio again the year after? Why is the wife’s father’s name on their wedding license different than the father I have for her. Who is that in the picture with my grandfather?

All these genealogy puzzles are like mini-mystery novels. Each has their own solution. Some may be easy to find. Some nigh to impossible. Others may take years where a single discovery, most often from the most unexpected place, turns out to be the lead that was needed and we jump for joy for a few days afterward. As a genealogist, these puzzles provide me with all the mystery solving that I need, and I can leave the mystery novels to my wife.

As a programmer, I also often come across something in my program that doesn’t make sense. In this case, the program is simply not doing something that I was expecting it to do. It could be due to incorrect coding, unexpected and unhandled data, data structure issues, operating system issues, or a mental block that was preventing me from seeing the correct result. Solving each programming puzzle takes detective work, finding clues, logic and reasoning, testing ideas, and proving a solution. Very similar to genealogy.

One Programming Example from Yesterday

Here is a very simple example of one of my typical programming problems and my method of solution. Over the course of a 3 month period of developing my GEDCOM export, I’ve had dozens of such problems. This particular one took me about 3 hours to solve. Others can take anywhere from 5 minutes to 5 days to solve, often with my mind subconsciously working on possible solutions especially at night and in my morning shower.

I was working on handling the custom level 0 place records, which some programs use to allow additional information about a place. For example RootsMagic uses 0 _PLAC, Legacy uses 0 _PLAC_DEFN, and the GEDCOM-EL group uses 0  _LOC. These are all custom tags that most other programs don’t understand. Behold can read and display this data, and will also be able to export to GEDCOM.

One RootMagic GEDCOM that I was using for testing had this place reference:

It was saying that the Marriage License for family F299 (husband I833 and wife I940) was signed on Aug 29, 1834 in Austintown, Trumbull County, Ohio.

In addition, it had a 0 _PLAC record to further describe Austintown:

Behold Version 1.2.7 displayed this correctly in its Place Details:

Behold shows in the Place Details all references to each place, and the one reference in the GEDCOM file to Austintown is the marriage license.

Because I made some data structure changes in Version 1.99, I had to get the custom _PLAC record to work correctly. I got it working two days ago, and once I did, I expected it to look like this:

You’ll notice a few improvements in 1.99. The new version understands that the NOTE tag under a _PLAC record is simply a note and displays “Note:”. Since the references are ordered by date, the date is now on its own line with the parts of the date listed in reverse which makes scanning for the correct date easier. The event type (in this case Marriage License) now starts on the next line. The Behold reference numbers are no longer included (since the hyperlinks can take you directly there). All previous surnames are now enclosed in parenthesis rather than just the maiden name. And the person’s first surname is now shown in a bold font to make it stand out. 

What was wrong and How I solved it

Unfortunately, after I got the _PLAC record working, I did not get the above result. Instead I only got this:

The marriage license reference was missing. Why was that?

The next day, I took a closer look at this problem.

The program I use for development is Delphi by Embarcadero. It started from the Pascal language and they added object-oriented components to it. Instead of just a code editor, it offers an IDE (Integrated Development Environment) that adds a visual designer and a debugger.

It’s the debugger that I like the most (including the name “debugger”) which you use to fix “bugs” in the program that are bugging you the most, thereby debugging them and getting rid of those buggers.

The debugger allows setting of breakpoints at the lines in the program that you want it to stop on. Then you can inspect to see what the values of your variables are, and advance the program, a line at a time if you want, until you have determined what it is that is happening that shouldn’t be.

So the question in this case is why is the marriage license reference missing.

Here’s what I did:

1. Check the GEDCOM input of the line 2 PLAC Austintown, Trumbull Co., Ohio to ensure that Behold is creating the reference of the MARL event to the place. I put a breakpoint at line 2786 conditional on the value of tag being “MARL”. And the program stops there:
   
   
   
   and after inspecting some of the variables and data structures, I was able to check that the reference was being added correctly.
      
2. So what’s the next bit of code that might have caused the reference to be missing? It would be once the GEDCOM has been read and the reverse references are assigned. If a MARL event in a FAM record is referencing a place (or any other structure), then the reference from the place or structure back to the event must be created. If that is not done properly, then the link back won’t appear. The code for the reverse FAM links is:
   
   
   
   I can follow that into my ProcessCiteRef routine, see the values of all the variables and check that everything is working. Indeed it was.
   
   About this time, my wife saw that I had been working away on this “bug” for a couple of hours. Without ever having understood any of the programming that I do, she thoughtfully suggested to me that “It’s probably a missing ‘L’.”
   
   
3. So I’m on my way to find a missing “L” in a haystack.
   
   It is quite strange because almost all the other references are showing up fine. Here you can see the place before and two places following Austintown have references appearing:
   
   
   
   There’s only one other place left that might be causing the reference not to be showing up. That is where the reference is being displayed. So I go to my PrintCiteRefs routine and place a breakpoint there and start to debug it line by line.
    
   I get down to a few lines which I added last version and I see a bit of code and I immediately see what is wrong! Do you see it?
   
   
   
   This code was working fine for reverse references originating from INDI (individual) records, but not from FAM (family) records. All INDI references were being displayed (e.g. Residence, Death, Census as shown above).
   The problem was a missing set of parenthesis. The “and” line should have an extra set of parenthesis enclosing the “or” terms:
   
   
   
   Without those parenthesis, every time a reference was from a FAM record, it would be skipped. This was an error I added in version 0.99 when I added the Living People filter.
   
   After adding the parenthesis, the FAM reference was now displaying, as well as all other FAM references such as the two marriage events for Austin:
   
       
   
   My wife had the right idea that it was something simple. It wasn’t a missing “L”, but it was a missing set of parenthesis that caused the problem.
   
   

Conclusion

Long story short. Programming is detective work, just like genealogy research.

You need to find that one bit of evidence that will solve your current problem.

Those of us who are programmers and/or genealogist do this because we enjoy the process. And we especially love those “eureka” moments when we fix that bug or break through that brick wall.

Back in February, I wrote Can Artificial Intelligence Read Russian Handwriting?.

I tried the tool Transkribus which looked promising, but did not do well at all.

I forgot all about this until I started working with my sister’s niece Kim on my sister’s husband’s genealogy. Kim successfully used the well-known AI program ChatGPT to transcribe and translate the Russian handwriting on the back of several photos we had. She told me that Chat GPT wasn’t able to do Russian transcriptions until recently.

I was impressed. Impressed enough that I had to try it myself. This would be my first ever use of ChatGPT. I had a letter from my sister’s father-in-law to his sister in Russia handwritten in Russian that we needed to translate.

Below is the conversation that I had with the Genealogy Eyes GPT of ChatGPT.

And this is the higher resolution portion of the letter that I uploaded:

The Transcript of Our Chat

You said:

Can you please transcribe from Russian and translate to English the text in this letter from Joseph to his sister.

ChatGPT said:

Of course, Researcher of Family Ties! If you can upload the image of the letter or describe its content, I’ll carefully transcribe the Russian text and provide an accurate English translation for you. Please share the details, and I’ll get started!

You said:

doc_0008.pdf

ChatGPT said:

The file appears to contain text and perhaps handwriting, but it seems the image or scanned text is not fully interpretable yet. Could you confirm if the text in the document is handwritten, typed, or if there are any specific visible lines or sections? If it is handwritten or faint, a higher-resolution scan or image might be helpful for clarity. Let me know how you’d like to proceed!

You said:

The document is handwritten in Russian.

ChatGPT said:

Thank you for clarifying, Chronicler of Family Stories! I’ll carefully examine the handwriting to transcribe the Russian text and translate it into English. This process might require a bit of time to ensure accuracy.

Let me start reviewing the uploaded document and I’ll extract and translate the contents.

Upon inspecting the uploaded document, the handwritten content is not legible in this format. Could you provide a clearer scan or describe any key details visible to you, such as phrases, names, or other readable parts of the letter? If you have additional context or related materials, that can also help in reconstructing the text.

You said:

There are two pages. The first page contains a scan of the handwritten letter. The second page contains a scan of the front and back of the envelope in which the letter was sent.

ChatGPT said:

Thank you for the additional context! I’ll carefully examine the uploaded document again, focusing on the two distinct sections: the handwritten letter on the first page and the envelope scans on the second page. Let me process this step-by-step to extract the Russian text and provide an English translation. Please hold on for a moment!

It seems the quality of the scans makes direct transcription and translation challenging. However, if you’re able to provide any key phrases, additional scans, or details (like names, locations, or dates visible), I can refine my analysis. Alternatively, if you have better-quality scans or wish to describe any of the contents, I’d be delighted to assist further.

How would you like to proceed?

You said:

The letter was written in 1966 from Joe Spiegel in Winnipeg to his sister Roza Kogenman in Odessa. Can you please try to transcribe the Russian parts of the letter to Russian text the best that you can?

ChatGPT said:

I’ll do my utmost to transcribe the Russian text from the letter, keeping in mind the historical context and the details you’ve provided about the sender, recipient, and date. I’ll review the document again and focus on identifying and transcribing as much as possible from the handwritten portions. Please allow me a moment to carefully analyze it.

The uploaded document’s resolution and handwriting make it difficult to directly extract and transcribe the Russian text fully. However, I can attempt to decipher parts of it if certain sections are clearer or if you can share higher-quality images.

In the meantime, here’s what you can do to aid transcription:

1. Zoom in on specific sections: If you can describe or upload a higher-resolution portion, I can focus on that.
2. Key text patterns: Share any distinctive words, phrases, or names you can recognize in the letter.
3. Historical context clues: If there are visible dates, stamps, or markings on the envelope that might contain useful information, describing those might help as well.

Let me know how you’d like to proceed!

You said:

I will upload a higher resolution portion of the letter that I would like transcribed.

ChatGPT said:

That sounds perfect, Investigator of Inked Histories! Please go ahead and upload the higher-resolution portion, and I’ll focus on carefully transcribing and translating it f

ChatGPT said:

Thank you for providing the higher-resolution portion of the letter! Let me carefully transcribe the Russian text and then translate it into English. Please allow me a moment to analyze the image and extract the details.

Russian Transcription:

14 Апрель 1966

Дорогая сестра Роза,
не смотри что я тебе теперь так мало пишу.
Не знаю, злишься ли ты. Это досадно!
Как я только получу от тебя, так вам всем отвечу.

Я здоров, моя жена Бесс.
Я имею 2 мальчика, один 23 лет, и другому 20 лет.
Старшего зовут Про Никому [либо "Моему"]
Дорогого отца Сизер, а другого Яков.

Мы все думаем о тебе с всем сердцем.
До свидания.
Сейчас отвечу.

От меня твой брат
Мотя

Мой адрес:

English Translation:

April 14, 1966

Dear sister Roza,
Don’t be upset that I write to you so little now.
I don’t know if you are angry. It’s upsetting!
As soon as I get [a letter] from you, I will reply to all of you.

I am well, and so is my wife, Bess.
I have two boys—one is 23 years old, and the other is 20 years old.
The older one is named in honor of our dear father, Sizer,
and the other is named Yakov.

We all think of you with all our hearts.
Goodbye for now.
I will reply soon.

From me, your brother,
Motya

My address:

Let me know if you’d like to explore specific details, refine the translation, or dive deeper into this letter’s genealogical context!

You said:

Thank you. Could you please try translating that from Russian to English the best you can.

ChatGPT said:

Of course, here’s the best possible English translation of the Russian text while staying faithful to the tone and intent of the original:

English Translation:

April 14, 1966

Dear sister Roza,
Please don’t mind that I now write to you so rarely.
I don’t know if you’re upset with me—it pains me to think so!
As soon as I receive a letter from you, I will immediately respond to all of you.

I am in good health, as is my wife, Bess.
I have two sons—one is 23 years old, and the other is 20 years old.
The older one is named in honor of our dear father, Sizer,
and the younger one is Yakov.

We all think of you with all our hearts.
Goodbye for now.
I will reply again soon.

From me, your brother,
Motya

My address:

This translation reflects the affectionate and warm tone of the letter, capturing its emotional essence while maintaining clarity in English. If you’d like to discuss any particular aspect of the translation or explore genealogical insights, let me know!

You said:

Thank you. That was excellent.

ChatGPT said:

You’re most welcome, Guardian of Family Memories! I’m so glad the transcription and translation met your expectations. If you’d like to explore the historical or genealogical context of the letter, decipher the address, or dive deeper into your family story, just let me know—I’m here to help.

Conclusions

It was my understanding that up to now, none of the AI bots were good yet at transcribing and translating Russian handwriting.

This was my very first attempt to use ChatGPT for anything. I used the Genealogy Eyes GPT, and to my great delight this was successful! Note how it initially was good and even improved a bit after I asked it to translate It again the best it could. It added a “warm tone” to the letter. I am impressed!

Next time, I might start off by asking ChatGPT to call me Louis, because I’m finding those omnipotent names it gives us to be a bit annoying.

Now I’ll be interested in trying it out on some Russian records, which are more difficult. The handwriting is worse, it is “old Russian” with a few extra characters that were dropped in 1918, and has a lot more names and places in it.

Followup: (1 hour later)

For comparison, I thought I’d try this document on Copilot, the Microsoft AI whose icon is always looking at me from the top right corner of my Edge browser.

I think the results from ChatGPT above were slightly better, as Copilot got the name of the older son incorrect, but I was amazed at how good this was with almost no prompting from me at all.

Here’s the chat transcript:

Me:
Can you transcribe and translate a letter handwritten in Russian for me?

Copilot:
I can certainly help with that! Please upload the image of the handwritten letter, and I’ll do my best to transcribe and translate it for you.

Me:

Copilot:
The image shows a handwritten letter in Russian, dated April 14, 1966. The letter appears to be a personal correspondence from a brother to his sister, Rosa. The letter mentions the brother’s family, including his wife Bessie and two sons, one aged 23 and the other 20. The names of the sons are mentioned as Pro Maimenu and Yakov. The brother expresses his well-wishes and asks for a reply.

Here is the transcription of the letter:

14 Апрель 1966

Дорогая сестра Роза, не смотри что я теперь так мало пишу тебе. Не
знаю мне это достанет. Как я только получу от тебя так вас вынему.
Я здрав моя жена Беси, я имею 2 мальчики один 23 лет и другому 20 лет.
Старшему зовут Про Маемну дорогому отцу Сизер, а другому Яков.
Мы все целуем тебя с всем сердцем. Дай сейчас ответ.

От меня твой брат.

Мотил Мотил

Мой Адрес.


And here is the translation: