Triple
T32937660
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Calendar (2003 film) |
E842574
|
entity |
| Predicate | directorCollaboratesWith |
P45033
|
FINISHED |
| Object | Paul Sarossy |
—
|
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: Paul Sarossy | Statement: [Calendar (2003 film), directorCollaboratesWith, Paul Sarossy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: directorCollaboratesWith Context triple: [Calendar (2003 film), directorCollaboratesWith, Paul Sarossy]
-
A.
coDirectedWith
Indicates that two or more entities jointly directed the same work or project.
-
B.
filmDirectorWorkedWith
chosen
Indicates that a film director has collaborated professionally with another person on one or more film projects.
-
C.
directorAssociatedWith
Indicates a relationship where a director is professionally connected to, responsible for, or involved with a particular entity (such as a work, organization, or project).
-
D.
leadActorPreviousCollaborationWithDirector
Indicates that the film’s lead actor has worked with the same director on at least one prior project.
-
E.
appearsInWorkCoDirectedBy
Indicates that an entity appears in a creative work that was directed by more than one director.
- 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_69f34949727c81909d195c97de3341c8 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69fd5f29b1988190877764ef2a399c7f |
completed | May 8, 2026, 3:57 a.m. |
| PD | Predicate disambiguation | batch_69fd5e30194c819085b5ce586122ab37 |
completed | May 8, 2026, 3:53 a.m. |
Created at: May 1, 2026, 1:20 a.m.