A recent 2nd cousin DNA match (click here for that story) inspired me to explore German records from Bavaria. So I decided to try AI to read the handwriting and translate it. First however, I did some more work on my Norwegians.
My home page at Claude
There is more than one free AI out there, so I ran an experiment. First I submitted a not great scan to all three of the better known ones, Claude, ChatGPT and Gemini. This is what I found:
- Claude told me it was hard to read and only gave me a partial.
- ChatGPT made stuff up that sounded totally plausible, but did not seem to be anything like the original Norwegian.
- Gemini made an effort to translate it and did well, but organized it into bullet items.
So my new method is to upload the same document to Claude and Gemini and merge the result. One thing I like about both of them is that they remember my recent efforts in the left hand sidebars (on Gemini ask for the sidebar in settings). So far I have not used either one heavily enough to be asked to upgrade to a paid version, unlike ChatGPT which has already requested that.
Next I tried some handwritten German documents. In my opinion Gemini did the best job. Read on for how each AI performed.
Claude told me for the first document “⚠️ Note: This register is in old German Kurrent script, which is very difficult to read with certainty. Several names and place names above are approximate — particularly “Fünfgam,” “Oberhafern,” and “Pößelfing.” If you need precise transcription for genealogical research, a specialist in Kurrent handwriting would be recommended.”
Now I asked about the death record of my great great grandmother, a Bavarian Catholic women who died in Munich. Click the image for the full record with column headings online.
Death record for Anna Reiner Riedleder
Claude attempted a translation and then said “The cause of death appears to be paralysis, she was 63 years old, died on January 21 at 3:30 AM, and was buried on February 2. She is listed as an Englishwoman.” I am totally puzzled by Claude thinking she was English.
ChatGPT stopped after a few lines
While Gemini said, “This entry is written in a late 19th-century German Kurrent/Sütterlin script and records a death.” Then proceeded to do a great job, column by column:
| Column Header (Translated) | German Transcription (Kurrent) | English Translation |
|
Fortlaufende Nr.
(Consecutive No.) |
62 | 62 |
|
Namen
(Names) |
Rissleiter
Anna |
Rissleiter (also spelled Rißleiter)
Anna |
|
Stand und Religion
(Status/Occupation & Religion) |
Taglöhnersehefrau, r. k. Aufenthaltsort, Hausnummer:
Mozartstr. 92/0 |
Day laborer’s wife, Roman Catholic. Residence & House Number:
Mozartstraße 92, ground floor (/0) |
|
Ledig, verheiratet…
(Single, married…) |
Ehefrau | Married woman (Wife) |
|
Arzt… Todesursache
(Doctor… Cause of Death) |
Paralys. cordis
Dr. Littrich |
Paralysis of the heart (Heart failure)
Dr. Littrich |
|
Tag, Monat, Jahr u. Stunde
(Day, Month, Year & Hour of Death) |
28. Jänner,
8 1/2 Uhr
A. M. |
January 28,
8:30
AM |
|
Tag der Beerdigung & Ort
(Day & Place of Burial) |
2. Feber,
öftl. |
February 2,
Eastern [Cemetery] |
|
Alter
(Age) |
63 Jahre | 63 Years |
|
Pfarrer…
(Pastor or Representative) |
Koop. v. St. Georg
Probst |
Cooperator (Assistant Pastor) of St. George,
[named] Probst |
|
Bemerkung
(Remarks) |
pr. 682 / 858 |
Abbreviation for a parish registry cross-reference or payment state (likely “protestantisch” notification or “praesentatum”).
Record numbers: 682 / 858 |
And Gemini’s commentary on this:
### Key Contextual Notes
Location Hint: The address Mozartstraße 92 and the cemetery abbreviation öftl. (Östlicher Friedhof / East Cemetery), alongside the parish of St. Georg, strongly point to this record being from Augsburg, Bavaria (matching the neighboring entry on line 60 which explicitly mentions Augsburg).
The Month: The scribe uses the Austrian/Southern German regional terms Jänner for January and Feber for February.
Cause of Death: Paralysis cordis is a standard Latin medical term used at the time for sudden cardiac arrest or heart failure.
Fascinating that the cause of death called “paralysis” is actually a heart attack.
I expect to continue my German and Norwegian research with these AI helpers.
I’ve just been working with Gemini on 18th century German and Latin birth/marriage/death records – overall I’m very happy with the results at this point, but it does need correction and/or instruction. As you found, it gave me the bulleted version of a transcript and translation first. I then asked for a full transcript and translation- which it gave me, but changed the order of the words a bit (and I was interested in the word-for-word of a birth record). So I prompted, “You said it starts with “x”, but it clearly starts “y” so I got an apology and finally it supplied what I asked for. It will find the same person or a likely spouse of that person on a record I gave it days earlier and points that out, sometimes suggesting the family probably has a connection to another village, which is helpful. It did hallucinate names of sponsors in one case – it was an odd situation where there were four godparents, not two, so it was confused – but I had pointed that out when I uploaded the image. I had to correct this error out twice, because it clung to its original names and tried to shoehorn them in.
I really like MyHeritage’s Scribe AI. I was shocked that it could both identify and translate (reasonably well, I think, not speaking the language) my grandmother’s Carpatho-Rusyn Eastern Slovakia dialect in family letters she saved.