Triple
T24567728
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ernestine Weaver |
E607838
|
entity |
| Predicate | sportLevelCoached |
P150912
|
FINISHED |
| Object | NCAA Division I |
—
|
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: NCAA Division I | Statement: [Ernestine Weaver, sportLevelCoached, NCAA Division I]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sportLevelCoached Context triple: [Ernestine Weaver, sportLevelCoached, NCAA Division I]
-
A.
sportsDisciplineCoachedOrManaged
Indicates that a person has coached or managed a particular sports discipline or type of sport.
-
B.
levelOfCompetitionCoached
chosen
Indicates the competitive level or tier at which an individual has coached.
-
C.
hasCoachedFor
Indicates that one entity has served in a coaching role for another entity, such as a team, organization, or individual.
-
D.
coachesSport
Indicates that one entity serves as the coach or trainer responsible for another entity’s participation in a particular sport.
-
E.
coachesLevel
Indicates the level or tier at which one entity coaches another, such as their rank, division, or proficiency category in a coaching context.
- 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_69e2c4cc35a48190990b7571bc086df8 |
completed | April 17, 2026, 11:39 p.m. |
| NER | Named-entity recognition | batch_69f2a9225d9c8190ae92e5540f6c45c2 |
completed | April 30, 2026, 12:58 a.m. |
| PD | Predicate disambiguation | batch_69f2a6b99e7c8190ba7e2dc8729a314a |
completed | April 30, 2026, 12:47 a.m. |
Created at: April 18, 2026, 2:28 a.m.