Triple
T1108223
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Salmon Fishing in the Yemen |
E25533
|
entity |
| Predicate | hasPoster |
P11912
|
FINISHED |
| Object | theatrical release poster |
—
|
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: theatrical release poster | Statement: [Salmon Fishing in the Yemen, hasPoster, theatrical release poster]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPoster Context triple: [Salmon Fishing in the Yemen, hasPoster, theatrical release poster]
-
A.
hasFilmPoster
chosen
Indicates that one entity serves as the film poster associated with another film entity.
-
B.
hasHomeMediaRelease
Indicates that a work has been released in a home media format (such as DVD, Blu-ray, or digital home release).
-
C.
hasIMDbId
Indicates that an entity is associated with a specific identifier used by the Internet Movie Database (IMDb) to uniquely reference it.
-
D.
hasEP
Indicates that an entity possesses, is associated with, or is characterized by a specific EP (e.g., an endpoint, event point, or designated EP resource) in the given context.
-
E.
servedInTheatres
Indicates that a film or performance was publicly exhibited in movie theaters or similar cinema venues.
- 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_69a49428d4448190b3b36991ceae87ce |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4b9e6134481909f348986a25f65c6 |
completed | March 1, 2026, 10:12 p.m. |
| PD | Predicate disambiguation | batch_69a4b749e2a881909ef28745a7d2d917 |
completed | March 1, 2026, 10:01 p.m. |
Created at: March 1, 2026, 7:43 p.m.