Triple
T6820229
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Martha Mengele |
E156878
|
entity |
| Predicate | residence |
P75
|
FINISHED |
| Object | Günzburg |
E273207
|
NE FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Günzburg | Statement: [Martha Mengele, residence, Günzburg]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Günzburg Context triple: [Martha Mengele, residence, Günzburg]
-
A.
Günzburg
chosen
Günzburg is a small Bavarian town in southern Germany, historically notable as the birthplace of Nazi physician Josef Mengele.
-
B.
Kaufbeuren
Kaufbeuren is a historic Bavarian town in southern Germany known for its well-preserved medieval old town and traditional Swabian culture.
-
C.
Eichstätt
Eichstätt is a historic Bavarian town in southern Germany known for its baroque architecture, Catholic university, and location within the Altmühltal Nature Park.
-
D.
Wolfratshausen
Wolfratshausen is a Bavarian town in southern Germany known for its historic old town, riverside setting on the Loisach and Isar, and proximity to Munich and the Alps.
-
E.
Forchheim
Forchheim is a town in Upper Franconia, Bavaria, Germany, known for its historic old town and location along major regional rail and road routes.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69c688298a288190af3f285d57f76bbe |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d359176c8190a34664ba2fcf7ee2 |
completed | March 27, 2026, 6:58 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c9e05085588190ba940f2a5280a57e |
completed | March 30, 2026, 2:30 a.m. |
Created at: March 27, 2026, 2:17 p.m.