Triple
T37001347
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duke vs. Michigan State (2015 NCAA Final Four) |
E915357
|
entity |
| Predicate | dukeHalftimeLead |
P186897
|
FINISHED |
| Object | 36–25 |
—
|
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: 36–25 | Statement: [Duke vs. Michigan State (2015 NCAA Final Four), dukeHalftimeLead, 36–25]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dukeHalftimeLead Context triple: [Duke vs. Michigan State (2015 NCAA Final Four), dukeHalftimeLead, 36–25]
-
A.
halftimeShow
Indicates a performance or entertainment event that takes place during the intermission between two halves of a game or match.
-
B.
hasHalftime
Indicates that an event, typically a game or performance, includes a designated halftime interval between its main segments.
-
C.
halftimeProducer
Indicates that one entity is the producer responsible for creating or organizing the halftime segment of an event, such as a sports game or show.
-
D.
halftimeShowTitle
Indicates the title given to a specific halftime show performance associated with an event.
-
E.
danceHall
Indicates a relationship where a location functions as a dance hall, i.e., a place designated or used for dancing activities or dance events.
- F. None of above. chosen
Provenance (4 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_69f76e8f1a8c81909db172ed31304971 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fb154c0fe08190a2e41e7a29b6055f |
completed | May 6, 2026, 10:17 a.m. |
| PD | Predicate disambiguation | batch_69f9fecc005c8190be082a8689193745 |
completed | May 5, 2026, 2:29 p.m. |
| PDg | Predicate description generation | batch_69fb154b5f8c819089103b41f51a1639 |
completed | May 6, 2026, 10:17 a.m. |
Created at: May 3, 2026, 4:14 p.m.