Triple
T21545103
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NCAA Division I men's basketball championship (head coach, 2021) |
E531602
|
entity |
| Predicate | titleGameScore |
P144175
|
FINISHED |
| Object | 86–70 |
—
|
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: 86–70 | Statement: [NCAA Division I men's basketball championship (head coach, 2021), titleGameScore, 86–70]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: titleGameScore Context triple: [NCAA Division I men's basketball championship (head coach, 2021), titleGameScore, 86–70]
-
A.
topScoringGame
Indicates that the referenced game has the highest score (or total points) among a set of games or within a specified context.
-
B.
gameWinningScoreBy
Indicates that a particular score is the decisive amount by which a game is won by an entity.
-
C.
JetsScore
Indicates that the team named Jets scores a certain number of points in a game or event.
-
D.
gameTitle
Indicates the name or title assigned to a particular game in the relationship.
-
E.
Game2Score
Indicates the scoring outcome or points achieved in the second game of a series or match.
- 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_69e0c45f17148190949c330ab9c27706 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69eeb58e38808190888f3501cf4fff7c |
completed | April 27, 2026, 1:02 a.m. |
| PD | Predicate disambiguation | batch_69e6320766308190ba5dca2f7c826aa4 |
completed | April 20, 2026, 2:02 p.m. |
| PDg | Predicate description generation | batch_69e633bf34c481909925d8dc1a633a65 |
completed | April 20, 2026, 2:10 p.m. |
Created at: April 16, 2026, 6:28 p.m.