Triple
T5586944
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | WNBA Finals |
E146778
|
entity |
| Predicate | previousFormats |
P64916
|
FINISHED |
| Object | best-of-three series |
—
|
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: best-of-three series | Statement: [WNBA Finals, previousFormats, best-of-three series]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: previousFormats Context triple: [WNBA Finals, previousFormats, best-of-three series]
-
A.
previousFormatUntil
Indicates that a prior format or state remained in effect up to, but not beyond, a specified point in time.
-
B.
formerPictureFormat
Indicates that an entity previously used a particular picture format before changing to a different one.
-
C.
previousFormatYears
Indicates the number of years during which a previous format, version, or configuration was in use before the current one.
-
D.
hadMultipleFormatsOverTime
Indicates that the same underlying item or entity has existed in more than one format or version at different points in time.
-
E.
packageFormat
Indicates the format or type in which a package is structured, encoded, or delivered.
- 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_69c009036c408190981a8d690b679b67 |
completed | March 22, 2026, 3:21 p.m. |
| NER | Named-entity recognition | batch_69c0209d713081908b39ee8befb2faf7 |
completed | March 22, 2026, 5:02 p.m. |
| PD | Predicate disambiguation | batch_69c01b16b9bc8190ab0b945507d90e05 |
completed | March 22, 2026, 4:38 p.m. |
| PDg | Predicate description generation | batch_69c01f4032408190a4f0d2eb21ebd870 |
completed | March 22, 2026, 4:56 p.m. |
Created at: March 22, 2026, 3:38 p.m.