Triple
T6137094
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UCLA–USC football rivalry |
E136859
|
entity |
| Predicate | typicalDayPlayed |
P34404
|
FINISHED |
| Object | Saturday |
—
|
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: Saturday | Statement: [UCLA–USC football rivalry, typicalDayPlayed, Saturday]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalDayPlayed Context triple: [UCLA–USC football rivalry, typicalDayPlayed, Saturday]
-
A.
primaryGameDay
Indicates the main or most significant day on which a game or sporting event is scheduled or typically played.
-
B.
typicalMatchDay
Indicates that the relationship or conditions described correspond to what normally happens on a standard or usual match day.
-
C.
typicalActivity
Indicates that an entity is commonly or characteristically engaged in a particular activity.
-
D.
typicalEventDay
chosen
Indicates the day on which an event is normally or most commonly held or occurs.
-
E.
typicalSchedule
Indicates the usual or standard timing and sequence of activities or events associated with an entity.
- 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_69c008a179388190a3b5a081bbf46d55 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c05c83aefc8190b0e250e96f2b10b4 |
completed | March 22, 2026, 9:17 p.m. |
| PD | Predicate disambiguation | batch_69c055f19b0c81908be34a00ab218723 |
completed | March 22, 2026, 8:49 p.m. |
Created at: March 22, 2026, 4:15 p.m.