Triple
T616464
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fiesta Bowl |
E14414
|
entity |
| Predicate | typicalKickoffTime |
P6833
|
FINISHED |
| Object | late December or early January |
—
|
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: late December or early January | Statement: [Fiesta Bowl, typicalKickoffTime, late December or early January]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalKickoffTime Context triple: [Fiesta Bowl, typicalKickoffTime, late December or early January]
-
A.
halftimeScore
Indicates the score or result of a game or match at the halfway point (halftime).
-
B.
typicalTimes
chosen
Indicates the usual or characteristic times at which an event, activity, or condition typically occurs.
-
C.
typicalSeasonTiming
Indicates the usual time period or season during which something normally occurs or is expected to take place.
-
D.
homeTeamUntil
Indicates that an entity serves as the home team for another entity up to (but not necessarily after) a specified time or event.
-
E.
gameWinningKicker
Indicates that an entity serves as the kicker responsible for securing the decisive, game-winning score in a contest.
- 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_69a4934b17c881909ace8270e8ddd202 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a49e22f3688190a512bec3f0347814 |
completed | March 1, 2026, 8:14 p.m. |
| PD | Predicate disambiguation | batch_69a49cfd15288190b4abdbd0bce3edcd |
completed | March 1, 2026, 8:09 p.m. |
Created at: March 1, 2026, 7:35 p.m.