Triple
T3146495
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Celtics Crossover Gaming |
E65775
|
entity |
| Predicate | hasHomeVenueType |
P21483
|
FINISHED |
| Object | esports arena |
—
|
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: esports arena | Statement: [Celtics Crossover Gaming, hasHomeVenueType, esports arena]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHomeVenueType Context triple: [Celtics Crossover Gaming, hasHomeVenueType, esports arena]
-
A.
hasSportsVenueType
Indicates that a sports venue is classified as being of a specific type or category (e.g., stadium, arena, court).
-
B.
hasProfessionalSportsVenue
Indicates that one entity possesses or hosts a venue specifically used for professional sports events.
-
C.
hasSportsTeamVenueFor
Indicates that a venue serves as the home or hosting location for a particular sports team.
-
D.
hostStadiumType
Indicates the type or category of stadium that serves as the host venue for an event or activity.
-
E.
homeStadiumType
chosen
Indicates the type or classification of a venue that serves as a team's primary home stadium.
- 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_69ad8582f564819088c27e1f96153938 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada598ccf08190b8817c456f38f2d7 |
completed | March 8, 2026, 4:36 p.m. |
| PD | Predicate disambiguation | batch_69ad9dfa3d9081908425aa636bb9b897 |
completed | March 8, 2026, 4:04 p.m. |
Created at: March 8, 2026, 3:05 p.m.