Triple
T24469539
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michigan–Michigan State men's ice hockey rivalry |
E617060
|
entity |
| Predicate | campusCityTeam1 |
P149915
|
FINISHED |
| Object | Ann Arbor, Michigan |
—
|
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: Ann Arbor, Michigan | Statement: [Michigan–Michigan State men's ice hockey rivalry, campusCityTeam1, Ann Arbor, Michigan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: campusCityTeam1 Context triple: [Michigan–Michigan State men's ice hockey rivalry, campusCityTeam1, Ann Arbor, Michigan]
-
A.
campusOfTeam
Indicates the campus or primary location associated with a particular team.
-
B.
campus1
Indicates a relationship where an entity is identified as a campus or is located on/associated with a particular campus.
-
C.
cityTeam2
Indicates that a team is based in, represents, or is associated with a particular city.
-
D.
hasCampusCity
Indicates that an educational institution or campus is located in a particular city.
-
E.
collegeTeamLocation
chosen
Indicates the geographic location (such as city, state, or region) associated with a particular college sports team.
- 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_69e2d7f197588190889a03e620558059 |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f299422cdc8190bc8d56243b7bc313 |
completed | April 29, 2026, 11:50 p.m. |
| PD | Predicate disambiguation | batch_69f287d76c7c81909494f12e606a9149 |
completed | April 29, 2026, 10:36 p.m. |
Created at: April 18, 2026, 2:20 a.m.