Triple
T21891421
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | WNBA conference finals |
E540556
|
entity |
| Predicate | formatBasis |
P130
|
FINISHED |
| Object | conference-based postseason format |
—
|
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: conference-based postseason format | Statement: [WNBA conference finals, formatBasis, conference-based postseason format]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formatBasis Context triple: [WNBA conference finals, formatBasis, conference-based postseason format]
-
A.
formsBasis
Indicates that one entity serves as the foundational support, justification, or underlying principle upon which another entity is built, derived, or depends.
-
B.
encodingBasisFor
Indicates that one encoding scheme serves as the foundational or reference basis for defining or interpreting another encoding.
-
C.
format
chosen
Indicates the specific arrangement, structure, or presentation style in which something is organized or expressed.
-
D.
baselineType
Indicates the type or category of a baseline used as a reference point for comparison or evaluation.
-
E.
namingBasis
Indicates that one entity serves as the reason, source, or criterion for how another entity is named or designated.
- 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_69e0c47a95908190ae3e19b716accb3d |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f11fc3727c8190b4d5d5a44aa2e55e |
completed | April 28, 2026, 8:59 p.m. |
| PD | Predicate disambiguation | batch_69e6be9a65888190a66598d62d20366c |
completed | April 21, 2026, 12:02 a.m. |
Created at: April 16, 2026, 7:06 p.m.