Triple
T34357413
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brian De Palma and Paul Schrader |
E881770
|
entity |
| Predicate | collaboratedOnFilm |
P115644
|
FINISHED |
| Object | Obsession |
—
|
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: Obsession | Statement: [Brian De Palma and Paul Schrader, collaboratedOnFilm, Obsession]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: collaboratedOnFilm Context triple: [Brian De Palma and Paul Schrader, collaboratedOnFilm, Obsession]
-
A.
workedOnFilmReleasedBy
Indicates that one entity contributed work to a film that was distributed or released by another entity.
-
B.
hasWorkedOnFilmBy
chosen
Indicates that one entity has worked on a film that was created, directed, or otherwise authored by another entity.
-
C.
partOfFilmographyOf
Indicates that a work (such as a film, show, or role) is included in the body of screen-related works credited to a particular person.
-
D.
featuredInFilmBy
Indicates that an entity is prominently included or showcased within a film that is created, directed, or produced by a specified person or organization.
-
E.
producedFilmStarring
Indicates that a person or company produced a film in which a specified actor or set of actors starred.
- 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_69f349bd06008190904c2f86c42749e3 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f71c35327c8190884f1bfe12bd2cd7 |
completed | May 3, 2026, 9:58 a.m. |
| PD | Predicate disambiguation | batch_69f71822d0e88190ac9731c7ae5a4def |
completed | May 3, 2026, 9:40 a.m. |
Created at: May 1, 2026, 1:58 a.m.