Triple
T8417414
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | James Franklin |
E198760
|
entity |
| Predicate | previousHeadCoachPosition |
P58548
|
FINISHED |
| Object | head football coach at Vanderbilt University |
—
|
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 football coach at Vanderbilt University | Statement: [James Franklin, previousHeadCoachPosition, head football coach at Vanderbilt University]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: previousHeadCoachPosition Context triple: [James Franklin, previousHeadCoachPosition, head football coach at Vanderbilt University]
-
A.
previousHeadCoach
Indicates that one entity formerly served as the head coach of the other entity before being replaced.
-
B.
coachPreviousPosition
chosen
Indicates that a coach previously held a specific position or role before their current one.
-
C.
returnedAsHeadCoach
Indicates that an individual resumed a previous role as head coach of a team or organization after a period of absence.
-
D.
headCoachEnd
Indicates the point in time or event at which an entity’s role or tenure as a head coach comes to an end.
-
E.
firstHeadCoach
Indicates that the referenced person served as the inaugural head coach of the specified team or organization.
- 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_69ca831201b481909e137936ef99ff11 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cb84c66b5c8190b9515f55dc08ac03 |
completed | March 31, 2026, 8:24 a.m. |
| PD | Predicate disambiguation | batch_69cb70d70ea081909c3dc1bd2ec14f85 |
completed | March 31, 2026, 6:59 a.m. |
Created at: March 30, 2026, 6:06 p.m.