Triple
T22638467
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gloria DeHaven |
E558749
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Richard Fincher |
—
|
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: Richard Fincher | Statement: [Gloria DeHaven, spouse, Richard Fincher]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Richard Fincher Context triple: [Gloria DeHaven, spouse, Richard Fincher]
-
A.
Richard Fincher
chosen
Richard Fincher is best known as the former husband of American actress and singer Gloria DeHaven.
-
B.
David Fincher
David Fincher is an acclaimed American film director and producer known for his dark, stylish thrillers such as Se7en, Fight Club, and The Social Network.
-
C.
Alan Parker
Alan Parker was a renowned British film director, producer, and screenwriter known for acclaimed works such as "Midnight Express," "Fame," and "Mississippi Burning."
-
D.
Alan Parker
Alan Parker is a British composer and guitarist known for his prolific session work and film and television scores.
-
E.
Roland Joffé
Roland Joffé is a British film director and producer best known for his Oscar-nominated work on politically charged dramas such as "The Killing Fields" and "The Mission."
- 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_69e24547f7fc819086e2c4ba3b979657 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1700f9fac8190b82190a54be22413 |
completed | April 29, 2026, 2:42 a.m. |
Created at: April 17, 2026, 3:04 p.m.