Triple
T9634026
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Clarkson Golden Knights women’s ice hockey |
E232881
|
entity |
| Predicate | NCAArunnerUp |
P68621
|
FINISHED |
| Object | 2013 |
—
|
LITERAL FINISHED |
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: 2013 | Statement: [Clarkson Golden Knights women’s ice hockey, NCAArunnerUp, 2013]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: NCAArunnerUp Context triple: [Clarkson Golden Knights women’s ice hockey, NCAArunnerUp, 2013]
-
A.
NCAATournamentRunnerUpFinishes
chosen
Indicates that a team finished as the runner-up (second place) in a specific NCAA Tournament.
-
B.
NCAAChampionship
Indicates that an entity has won, holds, or is otherwise associated with an NCAA (National Collegiate Athletic Association) championship title in a particular sport or event.
-
C.
NCAADivisionIITournamentAppearances
Indicates that an entity has participated in the NCAA Division II basketball tournament at least once.
-
D.
NCAAChampionshipBidType
Indicates the type or category of qualification by which an entity receives a bid to participate in an NCAA championship.
-
E.
NITchampionship
Indicates that an entity has won the championship title of the National Invitation Tournament (NIT) in college basketball.
- 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_69ca848940cc8190b97cec654cb3bb4a |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9b28ce2c819086d3c6e4e6ea95a7 |
completed | April 1, 2026, 10:24 p.m. |
| PD | Predicate disambiguation | batch_69ccd5acfa5c8190aaba3cf548723604 |
completed | April 1, 2026, 8:22 a.m. |
Created at: March 30, 2026, 8:11 p.m.