Triple
T1075060
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Matt Eberflus |
E23816
|
entity |
| Predicate | sportRole |
P15298
|
FINISHED |
| Object | coach in the NFL |
—
|
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: coach in the NFL | Statement: [Matt Eberflus, sportRole, coach in the NFL]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sportRole Context triple: [Matt Eberflus, sportRole, coach in the NFL]
-
A.
sportsBusinessRole
Indicates a professional role or position that an entity holds within the context of sports business or the sports industry.
-
B.
sportsCareer
chosen
Indicates a relationship where an entity’s professional involvement, roles, or achievements in sports are associated with a particular sport, team, period, or competitive level.
-
C.
sportFocus
Indicates that one entity has a primary emphasis, specialization, or concentration on a particular sport represented by the other entity.
-
D.
sponsorSport
Indicates that one entity financially or materially supports a sport or sporting activity, typically in exchange for promotion or association.
-
E.
primarySport
Indicates the main sport with which an entity (such as a person, team, or organization) is most closely associated or primarily involved.
- 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_69a493f1ddf48190a99d54b00e99f8ce |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b92e480c81909a848b48c196a293 |
completed | March 1, 2026, 10:09 p.m. |
| PD | Predicate disambiguation | batch_69a4b73ba8208190be7f3cef8c18689b |
completed | March 1, 2026, 10:01 p.m. |
Created at: March 1, 2026, 7:42 p.m.