Triple
T28656309
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Academy Award for Best Supporting Actress (won by Ruth Gordon) |
E725343
|
entity |
| Predicate | winnerCharacter |
P172380
|
FINISHED |
| Object | Minnie Castevet |
—
|
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: Minnie Castevet | Statement: [Academy Award for Best Supporting Actress (won by Ruth Gordon), winnerCharacter, Minnie Castevet]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: winnerCharacter Context triple: [Academy Award for Best Supporting Actress (won by Ruth Gordon), winnerCharacter, Minnie Castevet]
-
A.
winnerRole
Indicates the role or position held by the entity that is the winner in a given event or competition.
-
B.
winnerNickname
Indicates the nickname used to refer to the entity that has won a particular contest, event, or competition.
-
C.
winnerState
Indicates the state or condition of an entity that has achieved victory or been declared the winner in a given context.
-
D.
winnerAssociated
Indicates that there is a relevant connection or affiliation between a winner and another entity in the context of a particular event or competition.
-
E.
winnerManager
Indicates that one entity is the manager or supervisor of another entity who is the winner in a given context or competition.
- F. None of above. chosen
Provenance (4 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_69f01d84f5f0819087ab5e6143b14ed7 |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69f6abe15d5c81909ccf4ce37f78bc43 |
completed | May 3, 2026, 1:58 a.m. |
| PD | Predicate disambiguation | batch_69f6aa1c555081908787dbf76147f180 |
completed | May 3, 2026, 1:51 a.m. |
| PDg | Predicate description generation | batch_69f6aaf31a548190b2f792ff4b8c002a |
completed | May 3, 2026, 1:54 a.m. |
Created at: April 28, 2026, 4:55 a.m.