Triple
T6233745
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UNINTERRUPTED |
E139419
|
entity |
| Predicate | narrativeAngle |
P68374
|
FINISHED |
| Object | behind-the-scenes athlete stories |
—
|
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: behind-the-scenes athlete stories | Statement: [UNINTERRUPTED, narrativeAngle, behind-the-scenes athlete stories]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: narrativeAngle Context triple: [UNINTERRUPTED, narrativeAngle, behind-the-scenes athlete stories]
-
A.
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.
-
B.
narrativeSubject
Indicates that an entity functions as the main subject or focal point within a narrative or story.
-
C.
narrativeStrategy
chosen
Indicates the method or approach used to structure, present, or convey a story or sequence of events.
-
D.
narrative
Indicates that one entity tells, presents, or conveys a story or sequence of events about another entity or situation.
-
E.
narrativeFrame
Indicates the overarching narrative context or perspective within which events, actions, or relationships are presented or interpreted.
- 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_69c008b0e7ac8190808a59573ee646f3 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c062efa25c8190a54f5a6f5b5ad24f |
completed | March 22, 2026, 9:45 p.m. |
| PD | Predicate disambiguation | batch_69c05601de6481909d0880048fd7b49a |
completed | March 22, 2026, 8:50 p.m. |
Created at: March 22, 2026, 4:22 p.m.