Triple
T13481167
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Donnie Darko |
E318373
|
entity |
| Predicate | hasDirectorCutVersion |
P37393
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [Donnie Darko, hasDirectorCutVersion, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDirectorCutVersion Context triple: [Donnie Darko, hasDirectorCutVersion, true]
-
A.
hasDirectorCut
chosen
Indicates that a work (such as a film or episode) has an alternative version edited according to the director’s preferred vision.
-
B.
hasFilmVersionStatus
Indicates whether and how a work has been adapted into a film, specifying the status of that film version.
-
C.
hasCreatorForFilmVersion
Indicates that an entity is the creator (e.g., director, primary filmmaker) responsible for a particular film version of a work.
-
D.
hasCinematicShort
Indicates that an entity is associated with or includes a cinematic short film or short-form cinematic content.
-
E.
editedFilmForDirector
Indicates that one person performed film editing work on a movie under the direction or supervision of a specific 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_69d806b6bfec819089222715b2e86c8e |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69dbaf36c6b08190ba99400600e0b662 |
completed | April 12, 2026, 2:41 p.m. |
| PD | Predicate disambiguation | batch_69dbae06061881909a6a6032e0507587 |
completed | April 12, 2026, 2:36 p.m. |
Created at: April 9, 2026, 9:42 p.m.