Triple
T27667603
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Danny Green |
E697268
|
entity |
| Predicate | wonCollegeChampionshipWith |
P52009
|
FINISHED |
| Object | North Carolina Tar Heels men's basketball |
—
|
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: North Carolina Tar Heels men's basketball | Statement: [Danny Green, wonCollegeChampionshipWith, North Carolina Tar Heels men's basketball]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wonCollegeChampionshipWith Context triple: [Danny Green, wonCollegeChampionshipWith, North Carolina Tar Heels men's basketball]
-
A.
collegeChampionshipYear
Indicates the specific year in which a college team or individual won a championship title.
-
B.
wonConferenceChampionshipsIn
Indicates that an entity has secured one or more conference championship titles in a specified league, sport, or time period.
-
C.
wasNationalChampionship
Indicates that an entity held the title of national champion in a specified competition, sport, or event.
-
D.
hasWonNCAATitleIn
Indicates that an entity has won an NCAA championship title in a specified sport, category, or year.
-
E.
wonChampionshipAsPlayerWith
chosen
Indicates that one entity won a championship while playing on a team or alongside the other entity.
- 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_69ef590b85a4819083ec7c12bd3c9c10 |
completed | April 27, 2026, 12:39 p.m. |
| NER | Named-entity recognition | batch_69f634a50f3481908954bd4b691d6f19 |
completed | May 2, 2026, 5:30 p.m. |
| PD | Predicate disambiguation | batch_69f62c1a92648190835a2c5250d8c758 |
completed | May 2, 2026, 4:53 p.m. |
Created at: April 27, 2026, 2:39 p.m.