Triple
T23382913
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1983 NCAA Division I men's basketball championship game |
E593798
|
entity |
| Predicate | timeOfWinningBasket |
P152025
|
FINISHED |
| Object | at the buzzer |
—
|
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: at the buzzer | Statement: [1983 NCAA Division I men's basketball championship game, timeOfWinningBasket, at the buzzer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: timeOfWinningBasket Context triple: [1983 NCAA Division I men's basketball championship game, timeOfWinningBasket, at the buzzer]
-
A.
originalWinningTime
Indicates the time originally recorded as the winning performance in a competition or event.
-
B.
shotClock
Indicates that a time limit is imposed on an offensive possession or action, after which a violation occurs if a shot or required attempt has not been made.
-
C.
maximumScorePerDunk
Indicates the highest number of points that can be awarded for a single dunk action in the given context.
-
D.
playedBasketballFor
Indicates that one entity was a member of and competed for another entity’s basketball team.
-
E.
shotClockDuration
Indicates the length of time allotted on the shot clock for a team to attempt a shot before a violation occurs.
- 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_69e25d268a50819095f2fd479da8ef3f |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1a3b9287481908fd86c41f6d9fc53 |
completed | April 29, 2026, 6:22 a.m. |
| PD | Predicate disambiguation | batch_69f061dde2e481908308952f9c0d3c2e |
completed | April 28, 2026, 7:29 a.m. |
| PDg | Predicate description generation | batch_69f07cbbd7488190ab3c8ae7d0fb68bf |
completed | April 28, 2026, 9:24 a.m. |
Created at: April 17, 2026, 5:34 p.m.