Triple
T6002515
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2008 NCAA men's basketball championship |
E133629
|
entity |
| Predicate | KansasTitleCountAtTime |
P4419
|
FINISHED |
| Object | 3rd NCAA men's basketball championship (on the court) |
—
|
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: 3rd NCAA men's basketball championship (on the court) | Statement: [2008 NCAA men's basketball championship, KansasTitleCountAtTime, 3rd NCAA men's basketball championship (on the court)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: KansasTitleCountAtTime Context triple: [2008 NCAA men's basketball championship, KansasTitleCountAtTime, 3rd NCAA men's basketball championship (on the court)]
-
A.
titleCount
chosen
Indicates the number of distinct titles associated with an entity within a given context.
-
B.
titleNumber
Indicates the numerical designation or sequence number assigned to a title within an ordered set of titles.
-
C.
uniqueTitleHolderCount
Indicates the number of distinct entities that exclusively hold a given title, with no other entity sharing that same title.
-
D.
divisionTitleCount
Indicates the number of titles or championships associated with a particular division.
-
E.
totalFranchiseTitleNumber
Indicates the total count of titles associated with a given franchise across all its installments or entries.
- 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_69c00872444c8190bfaf1739dcec765c |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c04ee9cb0c8190a3361c36ac3944af |
completed | March 22, 2026, 8:19 p.m. |
| PD | Predicate disambiguation | batch_69c049e3316c819087ea635fa7ee8472 |
completed | March 22, 2026, 7:58 p.m. |
Created at: March 22, 2026, 4:05 p.m.