Triple
T32128367
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 37th Academy Awards |
E820566
|
entity |
| Predicate | bestShortSubjectCartoons |
P37210
|
FINISHED |
| Object | The Pink Phink |
—
|
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: The Pink Phink | Statement: [37th Academy Awards, bestShortSubjectCartoons, The Pink Phink]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bestShortSubjectCartoons Context triple: [37th Academy Awards, bestShortSubjectCartoons, The Pink Phink]
-
A.
bestShortSubjectCartoonProducer
Indicates that the subject is recognized as the top producer of short-format cartoon content featuring or about the given subject.
-
B.
bestShortSubjectCartoonWinner
chosen
Indicates that the subject has won an award for best short cartoon.
-
C.
bestShortSubjectOneReelWinner
Indicates that the subject has won the award for best short subject in the one-reel category.
-
D.
bestShortSubjectComedyWinner
Indicates that the subject is the winner of an award for best short-form comedy.
-
E.
mainCartoonBlock
Indicates that one entity serves as the primary or central cartoon programming block associated with another entity.
- 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_69f34902d42c819083a8e6bba9a8bb9a |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6c8159edc8190b1c87015e0c820e8 |
completed | May 3, 2026, 3:59 a.m. |
| PD | Predicate disambiguation | batch_69f6c3f42fbc8190a06eb1044c9e6094 |
completed | May 3, 2026, 3:41 a.m. |
Created at: May 1, 2026, 12:29 a.m.