Triple
T4884562
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dances with Wolves |
E109407
|
entity |
| Predicate | hasExtendedCutRuntime |
P42035
|
FINISHED |
| Object | approximately 236 minutes |
—
|
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: approximately 236 minutes | Statement: [Dances with Wolves, hasExtendedCutRuntime, approximately 236 minutes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasExtendedCutRuntime Context triple: [Dances with Wolves, hasExtendedCutRuntime, approximately 236 minutes]
-
A.
extendedEditionRuntimeMinutes
chosen
Indicates the duration, measured in minutes, of the extended edition version of a work.
-
B.
hasCut
Indicates that one entity has made or possesses a cut in, on, or through another entity.
-
C.
hasCutAfterRound
Indicates that an entity is eliminated or removed from participation after a specified round.
-
D.
hasDirectorCut
Indicates that a work (such as a film or episode) has an alternative version edited according to the director’s preferred vision.
-
E.
hasAlternateCut
Indicates that an entity has an alternative edited version or cut, distinct from its primary or original form.
- 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_69bd440f71348190b99938e59fb7f9a1 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6de253ac8190b1112da6953fa4f2 |
completed | March 20, 2026, 3:55 p.m. |
| PD | Predicate disambiguation | batch_69bd6c2be5e881909f6ec9c3bcde49f3 |
completed | March 20, 2026, 3:47 p.m. |
Created at: March 20, 2026, 1:27 p.m.