Triple
T36917066
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Texas Tech vs Michigan State |
E913071
|
entity |
| Predicate | MichiganStateCoach |
P149562
|
FINISHED |
| Object | Tom Izzo |
—
|
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: Tom Izzo | Statement: [Texas Tech vs Michigan State, MichiganStateCoach, Tom Izzo]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: MichiganStateCoach Context triple: [Texas Tech vs Michigan State, MichiganStateCoach, Tom Izzo]
-
A.
Michigan StateCoach
chosen
Indicates that a person holds or has held the position of head coach for a Michigan State University sports team.
-
B.
headCoachMichigan
Indicates that one entity serves as the head coach of the Michigan sports team associated with the other entity.
-
C.
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.
-
D.
WisconsinCoach
Indicates a person who serves or has served as a coach for a sports team representing the state or a school in Wisconsin.
-
E.
headCoachOhioState
Indicates that the subject is the head coach of the Ohio State sports team (typically the Ohio State University football team) during a given time period.
- 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_69f76e885b848190bad82c87e9525486 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fb34e5576881909394355c8ec6ddd2 |
completed | May 6, 2026, 12:32 p.m. |
| PD | Predicate disambiguation | batch_69fb2f6171e88190bf1e0ee6a644b6a9 |
completed | May 6, 2026, 12:09 p.m. |
Created at: May 3, 2026, 4:13 p.m.