Triple
T25066430
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2001 NHL All-Star Game |
E627794
|
entity |
| Predicate | goaltenders |
P34552
|
FINISHED |
| Object | Martin Brodeur |
—
|
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: Martin Brodeur | Statement: [2001 NHL All-Star Game, goaltenders, Martin Brodeur]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: goaltenders Context triple: [2001 NHL All-Star Game, goaltenders, Martin Brodeur]
-
A.
goaltender
chosen
Indicates a relationship where an entity serves as the goalkeeper or primary defender of the goal for a team in a game or sport.
-
B.
goaltendersTypicallyEligible
Indicates that certain individuals, usually those serving as goaltenders, are generally allowed or qualified to participate in a specified role, action, or category.
-
C.
goaltendersEligible
Indicates that certain goaltenders meet the required conditions to participate or be selected in a given context.
-
D.
losingGoaltender
Indicates that a particular goaltender is the one who was in net for the team that lost the game.
-
E.
hasNumberOfGoaltenders
Indicates the specific count of goaltenders associated with a given team, roster, or game context.
- 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_69e2ff2d71dc8190b4758e57d643cbe4 |
completed | April 18, 2026, 3:49 a.m. |
| NER | Named-entity recognition | batch_69f4599e14688190aa19833f62ffb283 |
completed | May 1, 2026, 7:43 a.m. |
| PD | Predicate disambiguation | batch_69f44d77f6e88190a4643ab2cbef567b |
completed | May 1, 2026, 6:51 a.m. |
Created at: April 18, 2026, 6:10 a.m.