Triple
T15883384
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stan Van Gundy |
E385128
|
entity |
| Predicate | collegeCoachingPosition |
P26683
|
FINISHED |
| Object | head coach at Castleton State College |
—
|
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: head coach at Castleton State College | Statement: [Stan Van Gundy, collegeCoachingPosition, head coach at Castleton State College]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: collegeCoachingPosition Context triple: [Stan Van Gundy, collegeCoachingPosition, head coach at Castleton State College]
-
A.
collegePosition
Indicates the role, title, or position an individual holds within a college or university.
-
B.
collegeCoach
chosen
Indicates that one entity serves as a coach for a college-level sports team associated with another entity.
-
C.
isCollegeCoachInSport
Indicates that a person holds the role of a college-level coach within a specified sport.
-
D.
playedForCollegeCoach
Indicates that an athlete was coached by a specific college coach while playing for that coach’s team.
-
E.
collegeTeamCoach
Indicates that one entity serves as the coach of a college sports team represented by the other 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_69d86da4e86481909f1325fdc971b5ec |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e174de2cd48190ab18e48c9f051a2a |
completed | April 16, 2026, 11:46 p.m. |
| PD | Predicate disambiguation | batch_69e142c3e18c8190bb7b023f4a0eaebb |
completed | April 16, 2026, 8:12 p.m. |
Created at: April 10, 2026, 4:51 a.m.