Triple
T10286096
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hattie McDaniel |
E241231
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Larry Williams |
E241231
|
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: Larry Williams | Statement: [Hattie McDaniel, spouse, Larry Williams]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Larry Williams Context triple: [Hattie McDaniel, spouse, Larry Williams]
-
A.
Larry Williams
chosen
Larry Williams was the husband of pioneering African American actress and Academy Award winner Hattie McDaniel.
-
B.
Keith Barish
Keith Barish is an American film producer and financier known for founding Keith Barish Productions and co-founding the Planet Hollywood restaurant chain.
-
C.
Larry Davis
Larry Davis is best known as a former husband of actress Kim Cattrall.
-
D.
Rex Walters
Rex Walters is an American former professional basketball player and college coach best known for his head coaching tenure at the University of San Francisco and his sharpshooting guard play at Kansas.
-
E.
Larry Steers
Larry Steers was a prolific American character actor of the silent and early sound film era, appearing in hundreds of movies in mostly uncredited or supporting roles.
- 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_69d381aaafc08190af475ef58dc16aba |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4d2b8343c819087c50e5471c46e3f |
completed | April 7, 2026, 9:47 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d6f84d432c8190a7d33e6c9f8ba8f2 |
completed | April 9, 2026, 12:52 a.m. |
Created at: April 6, 2026, 11:40 a.m.