Triple
T23319330
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bucknell Bison men's basketball |
E590802
|
entity |
| Predicate | JayWrightRole |
P151855
|
FINISHED |
| Object | former Bucknell player |
—
|
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: former Bucknell player | Statement: [Bucknell Bison men's basketball, JayWrightRole, former Bucknell player]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: JayWrightRole Context triple: [Bucknell Bison men's basketball, JayWrightRole, former Bucknell player]
-
A.
washingtonStateHeadCoach
Indicates that one entity serves as the head coach of the Washington State University athletic team associated with the other entity.
-
B.
Michigan StateCoach
Indicates that a person holds or has held the position of head coach for a Michigan State University sports team.
-
C.
UConnCoach
Indicates that a person serves or has served as a coach for the University of Connecticut (UConn) athletic program.
-
D.
BucksCoach
Indicates that the subject serves as a coach for the Milwaukee Bucks basketball team.
-
E.
westHeadCoachTeam
Indicates that a person serves as the head coach of a team in the Western conference or western division.
- F. None of above. chosen
Provenance (4 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_69e25d1d32188190948eb76909d1dcc3 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1978440888190b316664812105d60 |
completed | April 29, 2026, 5:30 a.m. |
| PD | Predicate disambiguation | batch_69effcf8ca2c8190887d4f4656617d21 |
completed | April 28, 2026, 12:19 a.m. |
| PDg | Predicate description generation | batch_69f01d88b4ec8190a2a17a88e0eda178 |
completed | April 28, 2026, 2:38 a.m. |
Created at: April 17, 2026, 5:07 p.m.