Triple
T27791441
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Steve Maltais |
E701090
|
entity |
| Predicate | notableLeagueTenure |
P26833
|
FINISHED |
| Object | American Hockey League |
—
|
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: American Hockey League | Statement: [Steve Maltais, notableLeagueTenure, American Hockey League]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableLeagueTenure Context triple: [Steve Maltais, notableLeagueTenure, American Hockey League]
-
A.
notableLeague
chosen
Indicates that there is a significant or prominent league associated with the subject entity.
-
B.
coachTenureIncludes
Indicates that a coach’s period of service or employment with a team or organization covers or includes a specified time span or event.
-
C.
notableDriverTenure
Indicates that an individual had a significant or distinguished period serving as a driver for a particular entity or organization.
-
D.
notableLeagueEra
Indicates that the subject is significantly associated with, or best known for participating in, a particular era or period of a sports league.
-
E.
careerSpanTeam
Indicates the team for which an individual’s entire career span (or a defined portion of it) is being measured or associated.
- 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_69ef6a50d8088190acbf3dfbb06d8091 |
completed | April 27, 2026, 1:53 p.m. |
| NER | Named-entity recognition | batch_6a00383e868c819098fd17e25fcbdb04 |
completed | May 10, 2026, 7:48 a.m. |
| PD | Predicate disambiguation | batch_6a0037cc59688190b7b9da939a413db3 |
completed | May 10, 2026, 7:46 a.m. |
Created at: April 27, 2026, 5:28 p.m.