Triple
T11684228
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ellen Geer |
E277696
|
entity |
| Predicate | relative |
P37
|
FINISHED |
| Object | Herta Ware |
E940758
|
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: Herta Ware | Statement: [Ellen Geer, relative, Herta Ware]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Herta Ware Context triple: [Ellen Geer, relative, Herta Ware]
-
A.
Herta Ware
chosen
Herta Ware was an American actress and political activist known for her work in film, television, and theater, as well as for her long marriage to actor Will Geer.
-
B.
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.
-
C.
Fay Hauser
Fay Hauser is an American actress and director known for her work in film and television since the 1970s, including roles in notable dramas and comedies.
-
D.
Marietta Lutze
Marietta Lutze was the wife of American psychiatrist, art collector, and philanthropist Arthur M. Sackler.
-
E.
Henrietta Treffz
Henrietta Treffz was an Austrian mezzo-soprano and opera singer of the 19th century, known both for her performances and for being the first wife of composer Johann Strauss II.
- 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_69d6aafe02d881909900d54ad7d4af84 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a463f6448190a4c8e1651a2bd905 |
completed | April 10, 2026, 7:19 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ef83098e2c819081c22462372f64b4 |
completed | April 27, 2026, 3:38 p.m. |
Created at: April 8, 2026, 9:40 p.m.