Triple
T3157487
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NBA franchise |
E66018
|
entity |
| Predicate | fanBaseType |
P28665
|
FINISHED |
| Object | local fans |
—
|
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: local fans | Statement: [NBA franchise, fanBaseType, local fans]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fanBaseType Context triple: [NBA franchise, fanBaseType, local fans]
-
A.
fanBase
Indicates that one entity is the group of admirers or supporters devoted to another entity.
-
B.
fanBaseScope
chosen
Indicates the extent or range of people who are considered fans or followers of an entity.
-
C.
fanBaseInteraction
Indicates interactions or engagements occurring between a fan base and the subject, such as communication, feedback, or participatory activities.
-
D.
fanBaseRelationship
Indicates a relationship in which one party is a fan or supporter of another, typically involving admiration, following, or dedicated interest.
-
E.
fanBaseLocation
Indicates the primary geographic area where an individual’s or group’s supporters or fans are predominantly located.
- 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_69ad85850c1481908a9e9c6242238de2 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada5ec0da88190a83f3448ac76e98e |
completed | March 8, 2026, 4:38 p.m. |
| PD | Predicate disambiguation | batch_69ad9dfbf0348190952a6bca8fc5fed1 |
completed | March 8, 2026, 4:04 p.m. |
Created at: March 8, 2026, 3:05 p.m.