Triple
T15323246
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Washington Coliseum |
E366346
|
entity |
| Predicate | hostedTeamSport |
P64218
|
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: [Washington Coliseum, hostedTeamSport, ice hockey]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hostedTeamSport Context triple: [Washington Coliseum, hostedTeamSport, ice hockey]
-
A.
hostsLeague
Indicates that one entity serves as the organizing or venue-providing host for a particular league.
-
B.
hostLeague
Indicates that one entity serves as the organizing league or governing competition framework for another entity, such as a team or event.
-
C.
hostsSport
chosen
Indicates that one entity provides the venue or location where a particular sport is played or conducted.
-
D.
sportsEventHosted
Indicates that a particular sports event was organized, arranged, or held by a specified host entity (such as a venue, organization, or city).
-
E.
sportsTenant
Indicates that one entity occupies or uses a sports facility or venue as a tenant under some form of agreement or arrangement.
- 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_69d85a121520819093dcce999fdefe1a |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03dd5ce0c819093c9a14de549dff6 |
completed | April 16, 2026, 1:39 a.m. |
| PD | Predicate disambiguation | batch_69deca9659f48190b8661df223ce5078 |
completed | April 14, 2026, 11:15 p.m. |
Created at: April 10, 2026, 3:16 a.m.