Triple
T34595747
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1973 NHL All-Star Game |
E888302
|
entity |
| Predicate | homeCoachTeam |
P48239
|
FINISHED |
| Object | Boston Bruins |
—
|
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: Boston Bruins | Statement: [1973 NHL All-Star Game, homeCoachTeam, Boston Bruins]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: homeCoachTeam Context triple: [1973 NHL All-Star Game, homeCoachTeam, Boston Bruins]
-
A.
coachingTeam
Indicates that one entity serves as a coach or coaching staff for a particular team.
-
B.
playerCoachTeam
Indicates a relationship where a player is coached by a specific coach while playing for a particular team.
-
C.
coachesTeamFrom
Indicates that a person serves as the coach of a sports team that is based in or represents a particular location or organization.
-
D.
feedsProfessionalTeam
Indicates that one entity provides food or catering services to a professional sports team.
-
E.
homeCoach
chosen
Indicates that a person serves as the coach of the home team in a particular game or competition.
- 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_69f349d3bfcc81909874c99e646fb3ea |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f728a345488190bd7e6751b09ac591 |
completed | May 3, 2026, 10:51 a.m. |
| PD | Predicate disambiguation | batch_69f7283ef2608190a7a85d7e7f5332c0 |
completed | May 3, 2026, 10:49 a.m. |
Created at: May 1, 2026, 2:03 a.m.