Triple
T3170396
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Something Good |
E66316
|
entity |
| Predicate | positionInNarrative |
P37669
|
FINISHED |
| Object | late in the film |
—
|
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: late in the film | Statement: [Something Good, positionInNarrative, late in the film]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: positionInNarrative Context triple: [Something Good, positionInNarrative, late in the film]
-
A.
positionInStory
chosen
Indicates the point or role an event, character, or element occupies within the overall sequence or structure of a story.
-
B.
locationOfNarrative
Indicates the place or setting where the events or story described in the narrative occur.
-
C.
narrativePerspective
Indicates the point of view or vantage from which a narrative is told, specifying the relationship between the storyteller and the events being described.
-
D.
narrativeImportance
Indicates the degree to which an entity or event is central, influential, or essential within the structure and progression of a narrative.
-
E.
hasNarrativeRole
Indicates that an entity participates in a narrative with a specific functional role (e.g., protagonist, antagonist, narrator) relative to the story.
- 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_69ad8585d7988190af37365331093ccd |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada64917e08190bf0466d2c5e43790 |
completed | March 8, 2026, 4:39 p.m. |
| PD | Predicate disambiguation | batch_69ad9e0076b4819094628f1ad10b8f68 |
completed | March 8, 2026, 4:04 p.m. |
Created at: March 8, 2026, 3:06 p.m.