Triple
T1501322
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Minnesota |
E33799
|
entity |
| Predicate | hasStateSport |
P2952
|
FINISHED |
| Object | Ice hockey |
—
|
LITERAL FINISHED |
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: Ice hockey | Statement: [Minnesota, hasStateSport, Ice hockey]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasStateSport Context triple: [Minnesota, hasStateSport, Ice hockey]
-
A.
hasSportsStatus
Indicates that an entity holds a particular sports-related status, role, or classification (such as amateur, professional, active, or retired) within a sporting context.
-
B.
stateSport
chosen
Indicates that a particular sport is officially associated with, designated by, or representative of a given state.
-
C.
hasEsport
Indicates that an entity is associated with or participates in a specific electronic sports (esports) activity or competition.
-
D.
hasSportingEvent
Indicates that a sporting event is associated with, held at, or organized by a given entity.
-
E.
hasAthlete
Indicates a relationship where an entity (such as a team, organization, or event) includes or is associated with one or more athletes.
- 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_69a885f352a4819099b24ff15489dede |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a90584b8b881908e112c7e59163812 |
completed | March 5, 2026, 4:24 a.m. |
| PD | Predicate disambiguation | batch_69a88727ce48819089b482cdc25453d1 |
completed | March 4, 2026, 7:25 p.m. |
Created at: March 4, 2026, 7:24 p.m.