Triple
T35773857
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Academy Award for Best Documentary Feature |
E1034236
|
entity |
| Predicate | genreRequirement |
P82410
|
FINISHED |
| Object | documentary |
—
|
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: documentary | Statement: [Academy Award for Best Documentary Feature, genreRequirement, documentary]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: genreRequirement Context triple: [Academy Award for Best Documentary Feature, genreRequirement, documentary]
-
A.
genreRestriction
Indicates that there is a limitation or constraint on which genres are allowed or applicable in a given context.
-
B.
genreWithin
Indicates that one genre is a subgenre or more specific category contained within another, broader genre.
-
C.
genreIncludes
Indicates that a broader genre category encompasses or contains a specified subgenre or work as part of its classification.
-
D.
targetGenre
chosen
Indicates the genre that something is specifically aimed at, categorized under, or intended to belong to.
-
E.
supportedGenre
Indicates that an entity (such as a system, service, or tool) is capable of handling, providing, or working with a specified genre.
- 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_69f76e14a1e081908eddd57bd6fdb3be |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7ac23d1388190bdf9628b294943bd |
completed | May 3, 2026, 8:12 p.m. |
| PD | Predicate disambiguation | batch_69f7ab734d848190a84f9b8c3a952b75 |
completed | May 3, 2026, 8:09 p.m. |
Created at: May 3, 2026, 4:06 p.m.