Triple
T36024836
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michigan–Minnesota football rivalry |
E1042097
|
entity |
| Predicate | homeStadiumForMichiganHomeGames |
P18826
|
FINISHED |
| Object | Michigan Stadium |
—
|
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: Michigan Stadium | Statement: [Michigan–Minnesota football rivalry, homeStadiumForMichiganHomeGames, Michigan Stadium]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: homeStadiumForMichiganHomeGames Context triple: [Michigan–Minnesota football rivalry, homeStadiumForMichiganHomeGames, Michigan Stadium]
-
A.
cityOfMichiganHomeGames
Indicates the city where the University of Michigan’s home games are played.
-
B.
cityOhioStateHomeGames
Indicates that a city in Ohio is the location where a team plays its home games.
-
C.
playsHomeGamesOn
chosen
Indicates that an entity regularly hosts its home games or matches at a specified location or venue.
-
D.
homeStadiumWhenOhioStateHosts
Indicates the stadium that serves as the home venue specifically when Ohio State is the hosting team in a game or event.
-
E.
homeStadiumMichiganState
Indicates that the referenced stadium serves as the home stadium for the Michigan State team or institution.
- 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_69f76e2c568881909e1e21f85252b0f0 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7b2c771108190adeec151daad5dab |
completed | May 3, 2026, 8:40 p.m. |
| PD | Predicate disambiguation | batch_69f7b1bad2e88190963ab4ee5d4f2038 |
completed | May 3, 2026, 8:36 p.m. |
Created at: May 3, 2026, 4:07 p.m.