Triple
T24052815
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pembroke State Braves men's basketball team |
E595707
|
entity |
| Predicate | earlyCareerStopFor |
P124314
|
FINISHED |
| Object | Kelvin Sampson |
—
|
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: Kelvin Sampson | Statement: [Pembroke State Braves men's basketball team, earlyCareerStopFor, Kelvin Sampson]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: earlyCareerStopFor Context triple: [Pembroke State Braves men's basketball team, earlyCareerStopFor, Kelvin Sampson]
-
A.
earlyCareerAt
chosen
Indicates that an entity spent the early part of its career working at or being affiliated with another entity.
-
B.
earlyCareerActivity
Indicates activities, roles, or engagements undertaken by an entity during the early stage of its career or professional development.
-
C.
interruptedCareerBy
Indicates that an entity’s career was halted, delayed, or disrupted by another specified event or circumstance.
-
D.
studCareerBegan
Indicates that a student's professional or academic career started at a specified time or institution.
-
E.
earlyCareerCoach
Indicates that one entity serves as a coach or mentor to another during the early stage of that other entity’s career.
- 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_69e288c184b081909f1f1751fb8e299a |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1d9d32f3c8190b48a77c844f4df8e |
completed | April 29, 2026, 10:13 a.m. |
| PD | Predicate disambiguation | batch_69f1764345388190a3102b62ddb729b4 |
completed | April 29, 2026, 3:08 a.m. |
Created at: April 17, 2026, 10:21 p.m.