Triple
T32971426
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Academy Award for Best Actress for Marvin's Room |
E843528
|
entity |
| Predicate | winnerActress |
P8116
|
FINISHED |
| Object | Frances McDormand |
—
|
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: Frances McDormand | Statement: [Academy Award for Best Actress for Marvin's Room, winnerActress, Frances McDormand]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: winnerActress Context triple: [Academy Award for Best Actress for Marvin's Room, winnerActress, Frances McDormand]
-
A.
bestActressWinner
chosen
Indicates that the subject has won the Best Actress award in a given competition or context.
-
B.
leadingActressNominee
Indicates that a person has been nominated for an award in the leading actress category for a particular work or performance.
-
C.
bestActressWinnerWork
Indicates the work (such as a film or performance) for which a person received a Best Actress award.
-
D.
bestActorWinner
Indicates that the subject is the recipient of a "Best Actor" award for a particular performance or event.
-
E.
academyAwardForBestActress
Indicates that an entity received the Academy Award for Best Actress in a leading role.
- F. None of above.
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_69f3494b9fc48190bb61c955ba471275 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f791cc969c8190bf187d6031a030d5 |
completed | May 3, 2026, 6:19 p.m. |
| PD | Predicate disambiguation | batch_69f791033d288190b118029fe412b9c9 |
completed | May 3, 2026, 6:16 p.m. |
Created at: May 1, 2026, 1:21 a.m.