Triple
T30757208
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2014 NCAA Division I men's basketball tournament |
E783119
|
entity |
| Predicate | finalFourAppearanceCountWisconsin |
P12670
|
FINISHED |
| Object | 3 |
—
|
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: 3 | Statement: [2014 NCAA Division I men's basketball tournament, finalFourAppearanceCountWisconsin, 3]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: finalFourAppearanceCountWisconsin Context triple: [2014 NCAA Division I men's basketball tournament, finalFourAppearanceCountWisconsin, 3]
-
A.
finalFourAppearancesWith
Indicates that the entities have appeared together in the NCAA basketball Final Four in the same tournament.
-
B.
FinalFourAppearances
chosen
Indicates the number of times a team has reached the semifinal round (Final Four) of a tournament or championship.
-
C.
finalFourAppearance
Indicates that an entity has reached the semifinal round (Final Four) of a tournament or championship.
-
D.
finalFourCountForChampion
Indicates the number of times a champion has reached the Final Four in the relevant competition or tournament.
-
E.
NCAAFinalFourAppearances
Indicates the number of times a team has reached the semifinal round (Final Four) of the NCAA football championship structure, if such a format is being referenced.
- 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_69fd64bc86848190a49f451a8fc5cf1e |
completed | May 8, 2026, 4:21 a.m. |
| PD | Predicate disambiguation | batch_69fd5ff4a648819090756d90fd195d9a |
completed | May 8, 2026, 4 a.m. |
Created at: April 29, 2026, 8:39 p.m.