Triple
T38535618
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | North Carolina vs. Michigan |
E923488
|
entity |
| Predicate | halftimeLeadMarginMichigan |
P191177
|
FINISHED |
| Object | 1 point |
—
|
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: 1 point | Statement: [North Carolina vs. Michigan, halftimeLeadMarginMichigan, 1 point]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: halftimeLeadMarginMichigan Context triple: [North Carolina vs. Michigan, halftimeLeadMarginMichigan, 1 point]
-
A.
halftimeScore
Indicates the score or result of a game or match at the halfway point (halftime).
-
B.
halftimeScoreLeader
Indicates which competitor or team was leading in score at the halftime point of a game or match.
-
C.
PackersHalftimeLead
Indicates that the Green Bay Packers are leading in score at halftime of a game.
-
D.
hasHalftime
Indicates that an event, typically a game or performance, includes a designated halftime interval between its main segments.
-
E.
cityOfMichiganHomeGames
Indicates the city where the University of Michigan’s home games are played.
- 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_69f76ea8f6348190a5c03fb6292bbee3 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fcdaa36f90819093f8661969990c7d |
completed | May 7, 2026, 6:32 p.m. |
| PD | Predicate disambiguation | batch_69fcd8fefc588190b063d7ea1ec87b07 |
completed | May 7, 2026, 6:25 p.m. |
| PDg | Predicate description generation | batch_69fcdaa2bfc08190beccabb0f1782d0d |
completed | May 7, 2026, 6:32 p.m. |
Created at: May 3, 2026, 4:32 p.m.