Triple
T30757179
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2014 NCAA Division I men's basketball tournament |
E783119
|
entity |
| Predicate | championShortName |
P55059
|
FINISHED |
| Object | UConn Huskies |
—
|
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: UConn Huskies | Statement: [2014 NCAA Division I men's basketball tournament, championShortName, UConn Huskies]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: championShortName Context triple: [2014 NCAA Division I men's basketball tournament, championShortName, UConn Huskies]
-
A.
teamNicknameChampion
chosen
Indicates that a particular nickname is used to refer to a team that has achieved champion status in a competition or league.
-
B.
championOf
Indicates that one entity serves as the primary defender, advocate, or leading supporter of another entity, often working to promote or protect its interests.
-
C.
championNationality
Indicates the country or nationality that a champion represents or is associated with.
-
D.
championOwner
Indicates that one entity is the owner or holder of a championship title associated with another entity.
-
E.
champion
Indicates that one entity has won a competition or contest and holds the top position or title over others.
- 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_69f224b047f48190b4f5efeb7ee97b37 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f6afebd7ec8190ab696f363d84abf0 |
completed | May 3, 2026, 2:16 a.m. |
| PD | Predicate disambiguation | batch_69f6aca3dedc81908b519d53d2909868 |
completed | May 3, 2026, 2:02 a.m. |
Created at: April 29, 2026, 8:39 p.m.