Triple
T22883436
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Benay Venuta |
E567536
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Armand Deutsch |
E583716
|
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: Armand Deutsch | Statement: [Benay Venuta, spouse, Armand Deutsch]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Armand Deutsch Context triple: [Benay Venuta, spouse, Armand Deutsch]
-
A.
Armand Deutsch
chosen
Armand Deutsch was an American film producer active during Hollywood's mid-20th century studio era.
-
B.
Helmut Dantine
Helmut Dantine was an Austrian-born American actor best known for his roles as suave or menacing European characters in classic Hollywood films of the 1940s, including "Casablanca."
-
C.
Anatole Dauman
Anatole Dauman was a prominent French film producer known for backing influential European art-house and New Wave directors.
-
D.
Armand Schaefer
Armand Schaefer was an American film director and producer known for his work on adventure serials and B-movies during the early 20th century.
-
E.
Ernest Schaufelberg
Ernest Schaufelberg was a theatre architect best known for designing the Adelphi Theatre in London.
- 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_69e2458a92ec81908fc1cd5f6407d2ab |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17f5dab048190a09c725dad123472 |
completed | April 29, 2026, 3:47 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0bca08d3348190b84e7d7d9b1e17fe |
completed | May 19, 2026, 2:25 a.m. |
Created at: April 17, 2026, 3:39 p.m.