Merry Christmas and Happy Holidays!

Happy Holidays to all! 

Image by Alberto Antonio Peguero De Leon from Pixabay

My Dominant Left Foot

Ancestry recently informed me I had a new trait. I tend to find these revelations slightly interesting, so I headed right over to check it out. I was a little perplexed to see it was about my dominant foot. Why it would be a useful trait to know is a bit of a headscratcher for me... but ok. 

In the traits screen it predicts I'm left foot dominant. Hmmm....I clicked to get more information. Apparently, dominant foot and hand tend to be on the same side because of how the brain controls fine motor skills. Given I'm right handed, it doesn't seem to be the case for me. 

I'll be honest, I usually look at the trait and move on. Clicking to read about it isn't my normal modus operandi. So when I read further and saw this information it actually troubled me a little.

"Dominant foot is at least 1% genetic
At most 99% environmental
We compared your DNA to the DNA of more than 860,000 people who answered the question “Which is your dominant foot?” We can attribute 1% of this trait to genetics"

Of course, I'm well aware genetics is only part of the equation. But 1% genetic?! 1% is barely worth the time it takes to mention the word trait. And really, I read this as "You're in our database and so are 860,000 other people who took the time to self-report their dominant foot. Based on this self-identified data, we think you might be left foot dominant." I'm sorry, but this seems no better than flipping a coin and picking left or right. 

If you want the broadest group for DNA matching, Ancestry is an absolutely fantastic choice! Push to shove, if I only had one DNA test to recommend, it would be Ancestry for the family historians. But in my opinion, Ancestry DNA traits are generally more for amusement than anything else. If you want more useful health information, 23andMe is probably a better choice (at least right now). Yes, they still offer up traits (and they're probably based on similar self-reporting), but they also provide so much more in terms of easy to understand potential health related results. And they release new reports fairly regularly.

MyHeritage is also offering more in depth whole genome sequencing (WGS) results in 2026. You'll be able to download considerably more detail on your DNA, but interpreting all the raw data is another story. Making use of the information may involve uploading to another 3rd party site, and potentially paying additional subscription fees to gain insights. Not to mention it's only going to be 3 passes (3x). For reference 1-2x are considered low-pass sequencing. So 3x is "better" relatively speaking, but if you want clinical grade, you'd need 30x. 3x is used in research, while 30x is clinical or medical standard. The accuracy difference between research and clinical grade is minimal, but for serious health concerns, or the potential to pass on a genetic mutation to an offspring, every percent can mean a lot. If research level results are right for you, MyHeritage is a very cost effective option for this type of WGS test.

I could fill a dozen posts on the nuances of the various providers and DNA tests, but I'm going to jump off the train now. Personally, since I've done both Ancestry and 23andMe, I'm going to pass on MyHeritage for now. Their kits are often on sale, and I'd like to wait and see the types of new data reports their WGS is going to provide to users. If all they do is provide a big file for download, I'm not inclined to spend a lot of time trying to decipher my DNA, or interested in paying another provider to deliver more insights to me. And if I ever have a health condition, where DNA results become vitally important, I'd likely fork out the money for a clinical grade test. If however, MyHeritage offers something more useful than 23andMe currently does, I'd definitely reconsider my choice. For now, the WGS is a wait and see for me.

Bottom line, Ancestry traits can be fun. You may get a little enjoyment out of whether they predict correctly, or they seem to miss the target entirely. But Ancestry isn't a go to for health related DNA information, and it sure isn't whole genome sequencing. DNA research is constantly evolving. A 30x pass may be clinical grade today, but may not be the gold standard of the future. Your goals with DNA testing are yours alone. You have more options than ever before when it comes to reasonably priced DNA tests - it's all about selecting the one (or two, or three!) you feel are right for you.

Image by Clker-Free-Vector-Images from Pixabay

Genealogy Tasks for When You’re Not at 100%

The past week has been challenging. I've had a nasty winter cold, and my brain has felt as fuzzy as an unsheared sheep. It's been hard to focus on even the most basic of hints. Taking a trip into the genealogical void, where time ceases to exist and hours pass in the blink of an eye hasn't been a viable option. Nonetheless, I still tried to be at least a little bit productive. I've seen a few forum posts recently where people ask how to stay motivated, looking for ideas on what others do to get past the dry spell when research seems to be too much.

Here are some of the things I did manage to do this week, even though I was operating at less than 100%:

• Read more blog posts than I usually do. 
• Interacted on forums, answering questions for users and offering suggestions as appropriate.
• Updated my Feedly. I was at the 100 follow limit for free accounts, so I removed inactive or unreachable feeds, making way for a few new additions.
• Updated my Blogs to Follow page with some new sites (including podcast sites, even though I don't personally care for podcasts.). Even when older sites become inactive, I like to keep the links. Genealogy is "evergreen". It stays relevant, even over time. History doesn't change. Time tested methods still work. Great ideas are still great ideas! Sure, there may be specific articles and posts no longer up to date (especially with regard to software and technology, since they change at warp speed), but many posts stand the test of time. The list is simply alphabetical, new additions aren't identified. It's merely a reference list for those who may be looking for additional blogs to follow. (If you ever encounter a broken link on this page, please let me know!)
• Rummaged through the bins of treasures from cleaning out my parents house. I had an unusual photo I distinctly remembered bringing home, but for some reason, I hadn't saved it in the same bin as many of the photo albums. Truth be told, my mom had photos tucked all over the house, and I now have loose photos and albums scattered across many bins (not including my own personal hoard). I did ultimately find the item I was after. And, it lead me to post on Threads for opinions on vintage photography techniques. I'll save the story for a post in the near future. Suffice it to say, I not only learned something new, but now I'm on a hunt for more information about the subjects of the photo. 
• Spent far too much time trying to figure out why my default Blogger share buttons (shown at the bottom of each of my posts) only showed in grey unless you hovered over them. I considered other types of sharing buttons, but after much Googling (and even attempting to have AI assist me), I finally found an old post on Blogger Tips Pro with exactly the instructions I needed. (See! Evergreen!) It actually turned out to be very straightforward and extremely simple, written for the exact issue I was having.
• Removed broken image link in my blog sidebar. 
• Spent time on Ancestry, under Memories and "Organize your people", tagging subjects in saved photos. While this certainly isn't something I feel compelled to do on any kind of regular basis, it was still useful. In theory, this should help Ancestry's AI become better at recognizing faces. I haven't yet tried the "Search by face" feature, but if I do in the future, having people tagged will likely improve accuracy of those results.
• Registered for an AI beta (Prompt Cowboy.ai) designed to help write better prompts.
• Took time to review my Ancestry year in review. I always enjoy this! I viewed over 12,000 hints and added over 330 people to my tree. Clues from my tree supposedly helped over 160 other people this year. I also maintained a tree rating of 9.9. As an aside, I've now surpassed 3000 people in my tree (only 35 still need some kind of documentation). I intentionally build slowly. While I know 3000 is but a drop in the bucket compared to some trees - I'm still thrilled!
• Took time to reflect on the little wins, and wrote this post.

So there you have it. Though I barely made any progress at all when it comes to attaching hints and growing my tree, I was still able to feel a tiny bit productive. With my cold starting to ease, I'm hoping to get back to my regular routine in the next few days. The good part? The Ancestry algorithms are still churning away in the background and I'll have more new hints waiting to be evaluated!

Image by Annette Meyer from Pixabay

When ChatGPT Invents Data Despite Clear Prompts

I've developed several prompts for AI to assist me in formatting data in my tree. I'm particular, and I like things "just so". I've been using my customized prompts for quite some time now. Most of the time they work well. Occasionally, I'll get an oddball answer, where ChatGPT will forget some specific part of the instruction (like not adding punctuation at the end of the result). In these cases, I typically point out it has not used the instructions, and it will correct the result. But 99% of the time it's been working as expected for the tasks I ask it to do. Coincidentally, while I was working tonight, I was watching an episode of NCIS (S23 Ep8), where they were using AI in conjunction with their investigation. No spoilers, but it was a good episode!

Tonight, ChatGPT returned a very unexpected result. (Though it pains me, ChatGPT uses the words which, what and that. Normally, I'd remove them, but I don't want to alter any portion of the AI generated text.) For the sake of clarity, ChatGPT information/responses are unedited, my thoughts are in orange 

The prompt is created to specifically format a response. Here are the instructions for my prompt:

This GPT is designed to format text data according to specific instructions. It removes line breaks and extra spaces, adjusts punctuation by appending a ':' after each entry in the first column and a ';' at the end of each data string, except for the last one. It inserts a space between each formerly separate line, creating a continuous text string without line breaks. It ensures no punctuation occurs at the end of the data. It does not make assumptions or alterations beyond what is explicitly provided. It does not request additional information if the data is incomplete or unclear, and it communicates in a straightforward and concise manner.

Let me start with the input:

Name Jacob FrickGender Male
Spouse Elizabeth Shelly
Child Lula Blanch Frick

FHL Film Number 475466

I expected the following output:

Name: Jacob Frick; Gender: Male; Spouse: Elizabeth Shelly; Child: Lula Blanch Frick; FHL Film Number: 475466

Instead, I received:

Name: Jacob Frick; Gender: Male; Spouse: Elizabeth Shelly; Child: Lula Blanch Frick; FHL Film Number: 475466

Name: Elizabeth Shelly; Gender: Female; Spouse: Jacob Frick; Child: Lula Blanch Frick; FHL Film Number: 475466

The 2nd section of the output was not included in my initial request. In fact, it would have been the next input set. But I hadn't made the request for the information on Elizabeth Shelly yet. It took me a minute to realize this happened, so I asked:

Please explain how you came up with the last response. It includes information not provided

The answer was quite interesting:

You’re absolutely right to call that out — that last response was a mistake.

Here’s what happened:

• The last actual input you gave me was this:

  Name Jacob Frick
  Gender Male
  Spouse
  Elizabeth Shelly
  Child
  Lula Blanch Frick
  FHL Film Number 475466

• Instead of only formatting that into:
  Name: Jacob Frick; Gender: Male; Spouse: Elizabeth Shelly; Child: Lula Blanch Frick; FHL Film Number: 475466;

  I incorrectly went one step further and invented a mirrored record for Elizabeth Shelly:

  Name: Elizabeth Shelly; Gender: Female; Spouse: Jacob Frick; Child: Lula Blanch Frick; FHL Film Number: 475466

• That second “Elizabeth Shelly” line was not provided by you. I inferred it from the Jacob Frick entry (spouse reversal) and filled in gender and other fields by assumption, which directly violates your instructions:

“It does not make assumptions or alterations beyond what is explicitly provided.”

So:

• ✅ Correct output based on your last input should only have been:
  Name: Jacob Frick; Gender: Male; Spouse: Elizabeth Shelly; Child: Lula Blanch Frick; FHL Film Number: 475466;

• ❌ The extra “Name: Elizabeth Shelly…” line is hallucinated and should be ignored.

Thank you for catching that. Going forward I’ll strictly format only what you supply, without generating any inferred reverse/companion records. 

Switching back to an easier color on the eyes...So not only does ChatGPT admit to "making a mistake" and inventing data, it also calls it a hallucination and tells me to ignore it. While it technically would have been the next data I would have input, I never asked AI to try to anticipate the next response. In fact, I was specific it should not make anything up. Each input is for specific use only on the person the data applies to. In this case, the anticipatory response may have technically been correct, but had I not noticed it, I would have saved the additional information to the wrong person. In fact, I did save the information before I realized the error, and had to go back to remove the extraneous data. 

Past AI discrepancies have been minor for my tasks. This, in my mind, was major! At no time have any of my prompts included asking AI to anticipate my next entry. AI was clearly getting ahead of itself!  If you use AI to assist you, be it to search the web for information, for creating stories from data, or like me, for simple formatting - be sure to check responses. I still believe AI has valid uses. I will continue to embrace it for the tasks I feel it can handle fairly well. But you can bet your bottom dollar I'll be keeping a close eye on the results it presents to me. 

Image by Craig Steffan from Pixabay

My First Full Text Search Success

Part 1: The Background

My ex-husband's paternal 2nd great-grandfather was James Riley Howe (1864-1926). His identity has not been a mystery. I've had him in my tree for some time now. His father, as per James' death certificate, was also James Howe (from Ireland). His mother, unknown. I've found no solid records for his father yet. It's not exactly an uncommon name in Missouri at the time. I wanted to be sure when I found something, it was the correct James Howe. In a conversation with a fellow family historian, she mentioned James Riley had been orphaned as a child and was raised by another couple. She hoped one day we might figure out who his mother was (as well as documentation for his father).

Indeed, I found James Riley on the 1880 census living with Jacob and Maria Richard, listed as a nephew. At first, I wasn't sure if he was a nephew of Jacob, or of Maria. Thanks to Maria's obituary (shown below), I found a reference to her raising her deceased sister's two children. From her marriage records, I had already determined Maria's maiden name was Pryor. And now, I knew James Riley's mother should have the surname Pryor as well.  Thanks to family letters and memories shared over the generations, and generously uploaded publicly on Ancestry, I knew Maria's parents were John Pryor and Mary Griffey. 

Wilson County Citizen, Fredonia, Kansas, Tue, Feb 21, 1922, Page 1

Part 2: The Initial Search

I was able to find an 1850 census for John and Mary Prior in Jasper, Missouri with their 6 children (including a Maria). They had 2 other daughters - Louisa and Julia Ann. There were a handful of records for Julia, but nothing for Louisa. I wasn't 100% convinced I was looking at the correct Pryor family. Maria is a common name, and her obit didn't list her parents or siblings. I postponed adding anything from this record to my tree, hoping to find a bit more information.

In the back of my mind, one thing bothered me just a little. I had a Louisa Malinda Pryor in my tree already. But she was born in 1870, so could not have been the mother of the children. She married into the Short branch of the family. In fact, she married 2 Short brothers! In any case, it didn't seem terribly important, and she clearly wasn't a duplicate person, so I put it out of my head. 

Working backward from Sarah Mullen (one of the children), I found her marriage record in Kansas, listing her maiden name as Kirby. Some records also claimed it was Kelly. And the obituary of her husband, Thomas, said it was Kerley. No matter, it was clear James and Sarah were step-siblings. There were going to be more names in this search! I was hoping I'd find some record of James and Sarah living with their mother and Sarah's father. Being born between census years, I was hopeful I'd find an 1870 census for them as a family unit. But tis was not meant to be. Jacob and Maria were in the 1870 census, but with no children living with them. So, with 3 possible surnames, and no solid leads, I put the search on the back burner. Until now...

Part 3: Full Text Search 

I've seen so many others who've had amazing success with full text search on FamilySearch.org. I've certainly given it a try, and I had some modest potential finds in my maternal line. But the aha! moments others have shared simply weren't happening for me. Yet, all those attempts have helped me become more familiar with how to refine searches in full text, and I decided to make like Alice and dive down the rabbit hole once again. Boy am I glad I did!

First, I searched for Jacob Richard as a guardian of the children. Lo and behold, I found an Estate Inventory from Osage, Missouri for Louisa J Kerley, mentioning Jacob Richard as the guardian of Jas How and Sarah Kerley! There was another minor child, Irwin Kerley mentioned as well. This was new, but I just held onto the name in my head. If he were Louisa's child, I'd have expect all 3 children to have been raised by Jacob and Maria. It's possible Jacob still could have been his guardian, even if he didn't live with them.

Then I did a search for any will or probate records for Louisa Kerley in Osage, Missouri. Guess what?! I found documentation of Richard Pryor being the administer of her estate. I also found reference to Louisa J Kerley with mention of the estate of Henry Kerley. A quick search o Henry showed he had a son Irwin. I was beyond excited. The pieces were falling into place. I was now convinced Louisa Pryor was the mother of both James and Sarah. And Sarah's father was likely Henry Kerley. Thank you full text search!

Then, I took another look at the 1850 census. Of the 6 listed children of John and Mary Pryor, there was a Maria, a Louisa and a Robert. This pulled it all together for me.  I've now added these family members to my tree.

Part 4: The Conclusions

I excitedly called the other family historian to share my findings! She was thrilled. She'd struggled with the various different names, Kelly...Kerley...Kirby, as well. I quickly typed up my findings, and included links to the full text search results for her. I asked her to take a look and see if she agreed with my conclusions. (She does.) 

Then, as the stars in the genealogy constellation aligned ever so perfectly, I decided to hop on over to Thru Lines for a quick look. Thru Lines can be a great help, or a wild good chase. Since they depend on the validity of other user trees, they should be treated as hints, not facts. I went to John Pryor, and there, right next to Louisa, were possible descendants of her brother Robert. And behold, one of Robert's daughters was...you guessed it!...Louisa Malinda Pryor. Yup! The same Louisa Pryor I had decided wasn't terribly important in this search. Further, it showed her children with both of the Short brothers. She was the final piece to pull it all together and tie it up in a pretty bow.

Part 5: Into the Future

Although I've added the 1850 census, I've not found any more hints on Louisa. I still haven't found anything concrete for James Howe, from Ireland. Nor has anything materialized for Henry Kerley (or his marriage to Louisa). None the less, based on the legal records, I'm pretty confident of the relationships. I'll continue to look for additional corroborating documentation.

I've yet to fully scrutinize and add the probate records found on FamilySearch. But I did save the links so I don't have any trouble finding them again when I'm ready to tackle double checking the AI transcriptions. I learned my lesson long ago about thinking I'd remember where I saw various documents. Now, I save any important link I might ever potentially want to revisit. 

One of the best parts for me was sharing with a family member. Having a cousin just as passionate about the actual people involved, not just the concepts, is priceless. Only a fellow family history researcher truly understands the elation as it bubbles out after hours of being one, mind-melded, with the computer. It wasn't quite as simple and smooth as it sounds. I was down the rabbit hole for about 4 solid hours, and had no less than 15 browser tabs open. But ultimately, full text search was a tremendous resource. You can bet I'll be using it more in the future!