Triple
T34233666
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Earle Bruce |
E878272
|
entity |
| Predicate | successorAsOhioStateHeadCoach |
P169894
|
FINISHED |
| Object | John Cooper |
—
|
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: John Cooper | Statement: [Earle Bruce, successorAsOhioStateHeadCoach, John Cooper]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: successorAsOhioStateHeadCoach Context triple: [Earle Bruce, successorAsOhioStateHeadCoach, John Cooper]
-
A.
predecessorAsOhioStateHeadCoach
Indicates that one coach previously held the position of Ohio State head football coach immediately before another coach.
-
B.
headCoachOhioState
Indicates that the subject is the head coach of the Ohio State sports team (typically the Ohio State University football team) during a given time period.
-
C.
successorHeadCoach
chosen
Indicates that one coach directly follows another as the next head coach of the same team or organization.
-
D.
successorAs49ersHeadCoach
Indicates that one person became the next head coach of the San Francisco 49ers after another person.
-
E.
Urban Meyer_laterBecame
Indicates that Urban Meyer subsequently assumed a later role, position, or status following a previously mentioned one.
- 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_69f349b22d8c819096b22df268382aa9 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69ffdf47d9608190830ca23d9cef6409 |
completed | May 10, 2026, 1:28 a.m. |
| PD | Predicate disambiguation | batch_69ffdf00e2b4819082dd5cb78f316baf |
completed | May 10, 2026, 1:27 a.m. |
Created at: May 1, 2026, 1:56 a.m.