Triple
T37001329
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duke vs. Michigan State (2015 NCAA Final Four) |
E915357
|
entity |
| Predicate | dukeCoach |
P186895
|
FINISHED |
| Object | Mike Krzyzewski |
—
|
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: Mike Krzyzewski | Statement: [Duke vs. Michigan State (2015 NCAA Final Four), dukeCoach, Mike Krzyzewski]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dukeCoach Context triple: [Duke vs. Michigan State (2015 NCAA Final Four), dukeCoach, Mike Krzyzewski]
-
A.
IndianaHeadCoach
Indicates that a person holds or has held the position of head coach for a sports team representing the state or institution of Indiana.
-
B.
SyracuseCoach
Indicates that an individual serves as a coach for a Syracuse University athletic team.
-
C.
NCAAChampionCoach
Indicates that a coach has led a team to win an NCAA championship title.
-
D.
UConnCoach
Indicates that a person serves or has served as a coach for the University of Connecticut (UConn) athletic program.
-
E.
notableCoachAlumnus
Indicates that a person is a notable former player or trainee of a particular coach.
- 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_69f76e8f1a8c81909db172ed31304971 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fb154c0fe08190a2e41e7a29b6055f |
completed | May 6, 2026, 10:17 a.m. |
| PD | Predicate disambiguation | batch_69f9fecc005c8190be082a8689193745 |
completed | May 5, 2026, 2:29 p.m. |
| PDg | Predicate description generation | batch_69fb154b5f8c819089103b41f51a1639 |
completed | May 6, 2026, 10:17 a.m. |
Created at: May 3, 2026, 4:14 p.m.