Triple
T31000253
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dark Horse (2011 film) |
E789915
|
entity |
| Predicate | followsFilmByDirector |
P115235
|
FINISHED |
| Object | Life During Wartime |
—
|
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: Life During Wartime | Statement: [Dark Horse (2011 film), followsFilmByDirector, Life During Wartime]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: followsFilmByDirector Context triple: [Dark Horse (2011 film), followsFilmByDirector, Life During Wartime]
-
A.
followsWorkByDirector
chosen
Indicates that one work comes after or is created subsequent to another work by the same director.
-
B.
followedByInFilm
Indicates that one scene, shot, or event in a film immediately succeeds another in the narrative or editing sequence.
-
C.
laterDirectedBy
Indicates that one entity was directed by another entity at a later time than some referenced or implied directing event.
-
D.
distributedFilmByDirector
Indicates that a director is responsible for distributing a particular film.
-
E.
followsInFilmography
Indicates that one work in a person’s filmography comes after another in chronological or credited order.
- 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_69f224c65a348190baaed1c01a29900c |
completed | April 29, 2026, 3:33 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: April 29, 2026, 8:56 p.m.