Triple
T38535617
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | North Carolina vs. Michigan |
E923488
|
entity |
| Predicate | halftimeScoreLeader |
P190873
|
FINISHED |
| Object | Michigan |
—
|
NE NERFINISHED |
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: Michigan | Statement: [North Carolina vs. Michigan, halftimeScoreLeader, Michigan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: halftimeScoreLeader Context triple: [North Carolina vs. Michigan, halftimeScoreLeader, Michigan]
-
A.
halftimeScore
Indicates the score or result of a game or match at the halfway point (halftime).
-
B.
hitsLeader
Indicates that an entity performs a hitting action on another entity who is in a leader role.
-
C.
leagueLeader
Indicates that the subject entity is currently ranked first or holds the top position within a specified league or competitive grouping.
-
D.
scoringLeaderGoals
Indicates that the subject is the leading scorer in terms of goals, having scored more goals than any other relevant participant in the given context.
-
E.
leagueLeaderIn
Indicates that an entity is the current top-ranked or leading participant within a specified league or competition.
- 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_69fcd34596288190b8e34a7a20b4c0db |
completed | May 7, 2026, 6 p.m. |
| PD | Predicate disambiguation | batch_69fcd1f81cbc8190b4fd3bfc3106c1f3 |
completed | May 7, 2026, 5:55 p.m. |
| PDg | Predicate description generation | batch_69fcd2e2f00081908b8c820fc073a63c |
completed | May 7, 2026, 5:58 p.m. |
Created at: May 3, 2026, 4:32 p.m.