Triple
T17741063
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wilhelm Furtwängler |
E442857
|
entity |
| Predicate | mother |
P120
|
FINISHED |
| Object | Adelheid Wendt |
—
|
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: Adelheid Wendt | Statement: [Wilhelm Furtwängler, mother, Adelheid Wendt]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Adelheid Wendt Context triple: [Wilhelm Furtwängler, mother, Adelheid Wendt]
-
A.
Adelheid Wendt
chosen
Adelheid Wendt was the mother of renowned German conductor and composer Wilhelm Furtwängler.
-
B.
Roswitha Eberl
Roswitha Eberl is a former East German sprint canoer who won multiple Olympic gold medals in the late 1970s and early 1980s.
-
C.
Margarete Gebhardt
Margarete Gebhardt was the wife of Austrian zoologist and Nobel Prize–winning ethologist Konrad Lorenz.
-
D.
Gertrud Strube
Gertrud Strube was the wife of German pathologist and Nobel laureate Gerhard Domagk, known for his pioneering work in antibacterial chemotherapy.
-
E.
Elisabeth Röhm
Elisabeth Röhm is a German-American actress best known for her role as Assistant District Attorney Serena Southerlyn on the television series "Law & Order."
- 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_69d8b9ed3a2081909b2ec0d4dd2f4c37 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e47acd780c8190b1308ef0aca00f5c |
completed | April 19, 2026, 6:48 a.m. |
Created at: April 10, 2026, 10:09 a.m.