Triple
T37001334
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duke vs. Michigan State (2015 NCAA Final Four) |
E915357
|
entity |
| Predicate | michiganStateRegion |
P190397
|
FINISHED |
| Object | East Region |
—
|
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: East Region | Statement: [Duke vs. Michigan State (2015 NCAA Final Four), michiganStateRegion, East Region]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: michiganStateRegion Context triple: [Duke vs. Michigan State (2015 NCAA Final Four), michiganStateRegion, East Region]
-
A.
Michigan StateConference
Indicates that a college or university’s athletic programs compete in the same athletic conference as Michigan State University.
-
B.
cityOfMichiganStateHomeGames
Indicates that the referenced city is the location where Michigan State plays its home games.
-
C.
Michigan StateScore
Indicates that a specified score is associated with Michigan State in a particular game or event.
-
D.
teamNicknameMichiganState
Indicates that a given nickname is used as the team nickname for Michigan State.
-
E.
homeStadiumMichiganState
Indicates that the referenced stadium serves as the home stadium for the Michigan State team or institution.
- 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_69fcc4b700748190ae00b21d09c96695 |
completed | May 7, 2026, 4:58 p.m. |
| PD | Predicate disambiguation | batch_69fcb0f9d3d881908a049475182fb039 |
completed | May 7, 2026, 3:34 p.m. |
| PDg | Predicate description generation | batch_69fcc4b5f22c8190b8b256adbdc2570c |
completed | May 7, 2026, 4:58 p.m. |
Created at: May 3, 2026, 4:14 p.m.