Triple
T27024949
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1991 NCAA Division I men's ice hockey national championship |
E680758
|
entity |
| Predicate | runnerUpTeamNickname |
P61387
|
FINISHED |
| Object | Terriers |
—
|
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: Terriers | Statement: [1991 NCAA Division I men's ice hockey national championship, runnerUpTeamNickname, Terriers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: runnerUpTeamNickname Context triple: [1991 NCAA Division I men's ice hockey national championship, runnerUpTeamNickname, Terriers]
-
A.
runnerUpNickname
chosen
Indicates that one entity is the nickname used for the runner-up position or second-place finisher in relation to another entity.
-
B.
stateOfRunnerUpTeam
Indicates the state or region associated with the team that finished as the runner-up in a competition or event.
-
C.
nicknameOfWinningTeam
Indicates that one entity is the nickname used to refer to the team that won a particular competition or event.
-
D.
runnerUpTeamOwner
Indicates the owner of the team that finished as the runner-up in a competition or league.
-
E.
runnerUpLeague
Indicates that an entity finished in second place in a league 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_69eeeb5450988190bfc9a3c012ac463a |
completed | April 27, 2026, 4:51 a.m. |
| NER | Named-entity recognition | batch_69f625411c14819086492062e86ba8d5 |
completed | May 2, 2026, 4:24 p.m. |
| PD | Predicate disambiguation | batch_69f623a91b9c8190b2e2fdbc55cb89b6 |
completed | May 2, 2026, 4:17 p.m. |
Created at: April 27, 2026, 7:10 a.m.