Triple
T6445986
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Independent Spirit Award for Best First Screenplay |
E138343
|
entity |
| Predicate | ceremonyUsuallyHeld |
P14854
|
FINISHED |
| Object | day before the Academy Awards |
—
|
LITERAL 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: day before the Academy Awards | Statement: [Independent Spirit Award for Best First Screenplay, ceremonyUsuallyHeld, day before the Academy Awards]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ceremonyUsuallyHeld Context triple: [Independent Spirit Award for Best First Screenplay, ceremonyUsuallyHeld, day before the Academy Awards]
-
A.
ceremonyHeld
Indicates that a formal ceremony or ritual event has taken place at a particular time and/or location.
-
B.
ceremonyHeldOn
Indicates that a specific ceremony took place on a particular date or day.
-
C.
ceremonyLocation
Indicates the place where a ceremony is held or takes place.
-
D.
ceremonyTiming
chosen
Indicates the temporal relationship specifying when a ceremony occurs or is scheduled to occur.
-
E.
ceremonyKnownAs
Indicates that a particular ceremony is referred to or recognized by a specific name or title.
- 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_69c008aa61ac8190bc96715ed79fe2d8 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c0698d866c81909ef3e0a53833ff7d |
completed | March 22, 2026, 10:13 p.m. |
| PD | Predicate disambiguation | batch_69c060faaf248190bbdc8ff909c8777a |
completed | March 22, 2026, 9:36 p.m. |
Created at: March 22, 2026, 4:46 p.m.