Triple
T16037329
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pappy Waldorf |
E389001
|
entity |
| Predicate | teamLedToBowlGame |
P102255
|
FINISHED |
| Object | California Golden Bears in the Rose Bowl |
—
|
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: California Golden Bears in the Rose Bowl | Statement: [Pappy Waldorf, teamLedToBowlGame, California Golden Bears in the Rose Bowl]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: teamLedToBowlGame Context triple: [Pappy Waldorf, teamLedToBowlGame, California Golden Bears in the Rose Bowl]
-
A.
coachedTeamInBowlGame
chosen
Indicates that a coach led or directed a particular team in a specific bowl game.
-
B.
bowlGame
Indicates that the relationship or event involves a postseason college football bowl game in which a team participates or that is associated with an entity.
-
C.
hasWonBowlGame
Indicates that a team or individual has achieved victory in a specific bowl game competition.
-
D.
menTeamPlaysIn
Indicates that a men's team participates or competes in a particular league, division, or competition.
-
E.
hasWonBowlGames
Indicates that one entity has achieved victories in one or more bowl games associated with another 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_69d86dada3808190825d5f80d72fbe88 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e1ff63edb0819092cbb671967bbdcd |
completed | April 17, 2026, 9:37 a.m. |
| PD | Predicate disambiguation | batch_69e1826f34c081908005bb736f1c485d |
completed | April 17, 2026, 12:44 a.m. |
Created at: April 10, 2026, 4:56 a.m.