Triple
T13413355
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 16th Academy Awards |
E320145
|
entity |
| Predicate | bestDocumentaryShortWinner |
P36461
|
FINISHED |
| Object | December 7th |
—
|
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: December 7th | Statement: [16th Academy Awards, bestDocumentaryShortWinner, December 7th]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bestDocumentaryShortWinner Context triple: [16th Academy Awards, bestDocumentaryShortWinner, December 7th]
-
A.
bestDocumentaryShortSubjectWinner
chosen
Indicates that the subject has won the award for Best Documentary Short Subject.
-
B.
bestDocumentaryFeatureWinner
Indicates that the subject is the winner of the Best Documentary Feature award in a given context or event.
-
C.
bestLiveActionShortFilmWinner
Indicates that the subject is the winner of the Best Live Action Short Film award in a given year or context.
-
D.
bestBritishShortFilmWinner
Indicates that an entity is the winner of the Best British Short Film award in a given context or event.
-
E.
bestAnimatedShortFilmWinner
Indicates that one entity is the winner of the Best Animated Short Film award in relation to the other entity (such as a specific year or award event).
- 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_69d806b943cc8190b6af624d385d7e12 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69dbaeb556948190af008c88e5bbf051 |
completed | April 12, 2026, 2:39 p.m. |
| PD | Predicate disambiguation | batch_69d9a0355de48190bb3fb96912e20df3 |
completed | April 11, 2026, 1:13 a.m. |
Created at: April 9, 2026, 9:35 p.m.