Triple
T11255218
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2023 NCAA Division I women’s basketball tournament |
E266418
|
entity |
| Predicate | finalFourEndDate |
P98740
|
FINISHED |
| Object | 2023-04-02 |
—
|
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: 2023-04-02 | Statement: [2023 NCAA Division I women’s basketball tournament, finalFourEndDate, 2023-04-02]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: finalFourEndDate Context triple: [2023 NCAA Division I women’s basketball tournament, finalFourEndDate, 2023-04-02]
-
A.
finalFourDateRange
Indicates the date range during which the Final Four event takes place.
-
B.
finalMatchDate
Indicates the calendar date on which the final or deciding match in a series, tournament, or competition takes place.
-
C.
nextFinals
Indicates that one event, match, or stage directly follows another as the subsequent or upcoming finals in a sequence.
-
D.
finalFourState
Indicates that a team or participant reached the semifinal round (Final Four) of a tournament held in a particular state.
-
E.
finalFourAppearance
Indicates that an entity has reached the semifinal round (Final Four) of a tournament or championship.
- F. None of above. chosen
Provenance (4 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_69d6aac7953c8190b82caf9d7640fdf9 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e9346f4c8190b29c2cf3a29cd1d1 |
completed | April 9, 2026, 6 p.m. |
| PD | Predicate disambiguation | batch_69d78793c00481908a3f764b610b77a4 |
completed | April 9, 2026, 11:03 a.m. |
| PDg | Predicate description generation | batch_69d796cf74308190a5b29d0dd82954a2 |
completed | April 9, 2026, 12:08 p.m. |
Created at: April 8, 2026, 9:31 p.m.