Triple
T5869646
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 3x3 basketball |
E130481
|
entity |
| Predicate | possessionAfterScore |
P67613
|
FINISHED |
| Object | defensive team immediately takes ball behind arc |
—
|
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: defensive team immediately takes ball behind arc | Statement: [3x3 basketball, possessionAfterScore, defensive team immediately takes ball behind arc]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: possessionAfterScore Context triple: [3x3 basketball, possessionAfterScore, defensive team immediately takes ball behind arc]
-
A.
scoreAfterPlay
Indicates the numerical score that results immediately after a specific play or action has been completed.
-
B.
scoreBeforePlay
Indicates that a particular score or point total existed prior to a specific play or action occurring.
-
C.
recognizedPossession
Indicates that an entity formally acknowledges or accepts another entity’s ownership or control over something.
-
D.
scoredFor
Indicates that one entity achieved points or a score on behalf of another entity, such as a player scoring for a team.
-
E.
isScoreFor
Indicates that one value represents the score or result associated with a particular entity, event, or performance.
- 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_69c0085047dc8190af24e311edad3c07 |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c044ffaef081909faaa7f420a3b9b7 |
completed | March 22, 2026, 7:37 p.m. |
| PD | Predicate disambiguation | batch_69c03347e51c81909053bcf34e3b88ab |
completed | March 22, 2026, 6:22 p.m. |
| PDg | Predicate description generation | batch_69c044fe17d08190b9bf47b13863ef52 |
completed | March 22, 2026, 7:37 p.m. |
Created at: March 22, 2026, 3:56 p.m.