Triple
T21124085
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Konrad Lorenz |
E520505
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Margarete Gebhardt |
—
|
NE NERFINISHED |
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: Margarete Gebhardt | Statement: [Konrad Lorenz, spouse, Margarete Gebhardt]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Margarete Gebhardt Context triple: [Konrad Lorenz, spouse, Margarete Gebhardt]
-
A.
Margarete Gebhardt
chosen
Margarete Gebhardt was the wife of Austrian zoologist and Nobel Prize–winning ethologist Konrad Lorenz.
-
B.
Margarete Weber
Margarete Weber was the wife of Albert Speer, the Nazi Germany architect and armaments minister.
-
C.
Margarete Kapp
Margarete Kapp was the wife of German right-wing politician Wolfgang Kapp, known for his role in the 1920 Kapp Putsch.
-
D.
Margarete Boden
Margarete Boden was a German nurse who became known as the wife of Heinrich Himmler, one of the leading figures of Nazi Germany.
-
E.
Gertrud Strube
Gertrud Strube was the wife of German pathologist and Nobel laureate Gerhard Domagk, known for his pioneering work in antibacterial chemotherapy.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b50a623881909c0bbaf4f2c055e7 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e72237c1a4819090987c645114d452 |
completed | April 21, 2026, 7:07 a.m. |
Created at: April 16, 2026, 2:56 p.m.