Triple
T3744251
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NBA game |
E79772
|
entity |
| Predicate | overtimeCondition |
P3313
|
FINISHED |
| Object | scores tied after regulation |
—
|
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: scores tied after regulation | Statement: [NBA game, overtimeCondition, scores tied after regulation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: overtimeCondition Context triple: [NBA game, overtimeCondition, scores tied after regulation]
-
A.
overtimeRule
chosen
Indicates the rule or policy that defines when and how overtime work is calculated or applied.
-
B.
formerOvertimeRule
Indicates that a previously applicable overtime rule or regulation no longer applies in the current context.
-
C.
overtimePeriodCount
Indicates the number of overtime periods that occurred or are allocated in a given event or context.
-
D.
overtimeFormatRegularSeason
Indicates the format or rules used for overtime periods specifically during the regular season.
-
E.
overtimePlayed
Indicates that an activity, event, or game continued beyond its regular or scheduled duration into an additional overtime period.
- F. None of above.
Provenance (3 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_69ad8b115610819095b02007da5ca3cb |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69adcb58c9048190a055d1f4a7e6b699 |
completed | March 8, 2026, 7:17 p.m. |
| PD | Predicate disambiguation | batch_69adc048f28c819092bed16a95a3cac1 |
completed | March 8, 2026, 6:30 p.m. |
Created at: March 8, 2026, 3:34 p.m.