Triple
T25993705
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2023 NCAA Division I men's basketball tournament |
E646426
|
entity |
| Predicate | bracketRegions |
P159645
|
FINISHED |
| Object | West Region |
—
|
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: West Region | Statement: [2023 NCAA Division I men's basketball tournament, bracketRegions, West Region]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bracketRegions Context triple: [2023 NCAA Division I men's basketball tournament, bracketRegions, West Region]
-
A.
bracketRegions
chosen
Indicates that one entity defines or marks the boundaries (start and end) of a region or span associated with another entity.
-
B.
compilerRegion
Indicates a relationship where a code element is associated with, or belongs to, a specific region or segment as defined by the compiler.
-
C.
usesRegionalBrackets
Indicates that one entity adopts or applies the style, format, or conventions of brackets specific to a particular region in relation to another entity or context.
-
D.
bracketRegionOfSyracuse
Indicates that one entity is a tournament bracket that encompasses or corresponds to the Syracuse region.
-
E.
separatesLinguisticRegions
Indicates that one entity serves as a boundary or divider between distinct linguistic regions or language areas.
- 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_69e77e88cb8481908da31d4a00661f55 |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f6054a859481908aa7275ec4859e4b |
completed | May 2, 2026, 2:08 p.m. |
| PD | Predicate disambiguation | batch_69f5aff889988190ad10bcf1a280f717 |
completed | May 2, 2026, 8:04 a.m. |
Created at: April 22, 2026, 8:57 a.m.