Triple
T35402098
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rebuilding Ball State football program |
E1023261
|
entity |
| Predicate | endCoachTenure |
P182929
|
FINISHED |
| Object | 2008 |
—
|
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: 2008 | Statement: [Rebuilding Ball State football program, endCoachTenure, 2008]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: endCoachTenure Context triple: [Rebuilding Ball State football program, endCoachTenure, 2008]
-
A.
coachTenureIncludes
Indicates that a coach’s period of service or employment with a team or organization covers or includes a specified time span or event.
-
B.
headCoachTenure
Indicates the duration or period during which a specific individual serves as the head coach of a team or organization.
-
C.
headCoachPreviousTenure
Indicates that a person served as the head coach of a team or organization during a prior period before the current tenure.
-
D.
teamTenure
Indicates the duration or length of time an entity has been part of a particular team.
-
E.
yearsActiveAsCoach
Indicates the span of time, typically in years, during which an individual has served in a coaching role.
- F. None of above. chosen
Provenance (4 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_69f76df43ca4819098711ca4370f1bb9 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7953c42c4819084cd4eb62b733c2c |
completed | May 3, 2026, 6:34 p.m. |
| PD | Predicate disambiguation | batch_69f7910770108190bdd39ddb5d304f54 |
completed | May 3, 2026, 6:16 p.m. |
| PDg | Predicate description generation | batch_69f791cad5e08190a8a04ca283dbecaa |
completed | May 3, 2026, 6:19 p.m. |
Created at: May 3, 2026, 4:03 p.m.