Triple
T38222971
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | San Diego State–Fresno State football rivalry |
E1012060
|
entity |
| Predicate | teamMascotInvolved |
P54414
|
FINISHED |
| Object | Aztec Warrior |
—
|
NE NERFINISHED |
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: Aztec Warrior | Statement: [San Diego State–Fresno State football rivalry, teamMascotInvolved, Aztec Warrior]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: teamMascotInvolved Context triple: [San Diego State–Fresno State football rivalry, teamMascotInvolved, Aztec Warrior]
-
A.
team2Mascot
chosen
Indicates that the second team in a given context has the specified mascot.
-
B.
mascotCollectiveName
Indicates that a mascot is associated with and represents a particular collective group, organization, or team name.
-
C.
mascotForSportLevel
Indicates that an entity serves as the mascot specifically for a given sport at a particular competitive or organizational level.
-
D.
mascotName
Indicates the name assigned to a mascot that represents an entity.
-
E.
isMascotCounterpartOf
Indicates that one entity serves as the mascot equivalent or counterpart of another entity, typically representing the same thing in a mascot form.
- 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_69f76dd25e0c81909f2abd0803e5e3ee |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fcc42cbac48190b8d3e4c9ce140838 |
completed | May 7, 2026, 4:56 p.m. |
| PD | Predicate disambiguation | batch_69fcb0fc69c88190800453eb57a7e62c |
completed | May 7, 2026, 3:34 p.m. |
Created at: May 3, 2026, 4:30 p.m.