Triple
T8418005
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Big East Coach of the Year |
E198776
|
entity |
| Predicate | winner |
P354
|
FINISHED |
| Object | Don Nehlen |
E732126
|
NE 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: Don Nehlen | Statement: [Big East Coach of the Year, winner, Don Nehlen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Don Nehlen Context triple: [Big East Coach of the Year, winner, Don Nehlen]
-
A.
Don Nehlen
chosen
Don Nehlen is a former American college football coach best known for revitalizing the West Virginia University football program and leading it to national prominence.
-
B.
Pat Keady
Pat Keady is best known as the wife of longtime Purdue basketball coach and Hall of Famer Gene Keady.
-
C.
Bill Belew
Bill Belew was an American fashion and costume designer best known for creating many of Elvis Presley’s iconic stage outfits and jumpsuits.
-
D.
Chip Diggins
Chip Diggins is a film producer best known for his work on the comedy-drama adaptation "A Walk in the Woods."
-
E.
Tubby Smith
Tubby Smith is an American college basketball coach best known for leading the University of Kentucky to the 1998 NCAA national championship and for his long, successful career across multiple major programs.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca8312d63c8190bf133b676b44a385 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cb84c66b5c8190b9515f55dc08ac03 |
completed | March 31, 2026, 8:24 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce1d469a148190a6f018f758cba5eb |
completed | April 2, 2026, 7:39 a.m. |
Created at: March 30, 2026, 6:06 p.m.