Triple
T33505061
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New England boxing scene |
E858088
|
entity |
| Predicate | hasAmateurTournament |
P74099
|
FINISHED |
| Object | New England Golden Gloves |
—
|
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: New England Golden Gloves | Statement: [New England boxing scene, hasAmateurTournament, New England Golden Gloves]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAmateurTournament Context triple: [New England boxing scene, hasAmateurTournament, New England Golden Gloves]
-
A.
hasTournament
chosen
Indicates that an entity organizes, hosts, or is associated with a specific tournament.
-
B.
hasProAm
Indicates that an entity possesses or is associated with a professional–amateur (pro-am) status, feature, or component.
-
C.
hasAmateurSection
Indicates that something includes or provides a dedicated section or part specifically for amateurs.
-
D.
hasAmateurLevel
Indicates that an entity possesses an amateur level of skill, experience, or proficiency in a given activity or domain.
-
E.
hasTournamentRecord
Indicates that an entity possesses a documented performance or results record in a specific tournament or set of tournaments.
- 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_69f3497660508190a541826a81f7e9ab |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f6e59ed5388190b4db22e945b40e20 |
completed | May 3, 2026, 6:05 a.m. |
| PD | Predicate disambiguation | batch_69f6e3db74c081909a991309d835d477 |
completed | May 3, 2026, 5:57 a.m. |
Created at: May 1, 2026, 1:38 a.m.