Triple
T36283651
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Larry Kehres |
E893009
|
entity |
| Predicate | collegeCoachingRecordType |
P76762
|
FINISHED |
| Object | football |
—
|
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: football | Statement: [Larry Kehres, collegeCoachingRecordType, football]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: collegeCoachingRecordType Context triple: [Larry Kehres, collegeCoachingRecordType, football]
-
A.
collegeRecord
Indicates that there exists a record documenting an entity’s association or history with a college (such as enrollment, attendance, or academic performance).
-
B.
coachingRecordCollegeTies
Indicates a relationship where a coaching record is associated with one or more colleges to which it is tied (e.g., where the coaching occurred or is attributed).
-
C.
collegeCoach
Indicates that one entity serves as a coach for a college-level sports team associated with another entity.
-
D.
overallCollegeCoachingRecord
chosen
Indicates the summarized win-loss (and often tie) coaching performance record of a college coach across all seasons and teams.
-
E.
collegeScoringRecord
Indicates that an entity holds or represents a record for scoring performance achieved during college-level competition.
- 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_69f76e4955c08190b8cfddca34fc0242 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fdd5fba5048190b7d430ae2054a1fd |
completed | May 8, 2026, 12:24 p.m. |
| PD | Predicate disambiguation | batch_69fdd35f76f88190a1854ea27132f9c7 |
completed | May 8, 2026, 12:13 p.m. |
Created at: May 3, 2026, 4:09 p.m.