Triple
T38535592
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | North Carolina vs. Michigan |
E923488
|
entity |
| Predicate | finalScoreNorthCarolina |
P199885
|
FINISHED |
| Object | 77 |
—
|
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: 77 | Statement: [North Carolina vs. Michigan, finalScoreNorthCarolina, 77]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: finalScoreNorthCarolina Context triple: [North Carolina vs. Michigan, finalScoreNorthCarolina, 77]
-
A.
finalFourCountForNorthCarolina
Indicates the number of times the University of North Carolina’s men’s basketball team has reached the NCAA Final Four.
-
B.
tournamentRegionOfNorthCarolina
Indicates that a tournament is located in or associated with the North Carolina region.
-
C.
homeArenaCarolina
Indicates that the specified arena serves as the home venue for the Carolina team.
-
D.
regionOfNorthCarolina
Indicates that a location or entity is situated within the geographic boundaries of North Carolina.
-
E.
NCOrank
Indicates a hierarchical ranking relationship between entities within the context of a non-commissioned officer (NCO) rank structure.
- 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_69ff6074bcd4819090b72cd6209ff206 |
completed | May 9, 2026, 4:27 p.m. |
| PD | Predicate disambiguation | batch_69ff600aba888190812a6e7eca0283b8 |
completed | May 9, 2026, 4:25 p.m. |
| PDg | Predicate description generation | batch_69ff607407a881909d9e6e1c98559a6e |
completed | May 9, 2026, 4:27 p.m. |
Created at: May 3, 2026, 4:32 p.m.