Triple
T31885070
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | QubicaAMF Bowling World Cup |
E813985
|
entity |
| Predicate | teamSizePerCountry |
P172694
|
FINISHED |
| Object | one man and one woman in most editions |
—
|
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: one man and one woman in most editions | Statement: [QubicaAMF Bowling World Cup, teamSizePerCountry, one man and one woman in most editions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: teamSizePerCountry Context triple: [QubicaAMF Bowling World Cup, teamSizePerCountry, one man and one woman in most editions]
-
A.
teamSizeVariantOf
Indicates that one entity represents a variation of another entity specifically in terms of team size configuration or composition.
-
B.
mostTeamsInCountry
Indicates that an entity has the highest number of teams located within a given country compared to all other entities.
-
C.
maximumTeamsPerNationPerGender
Indicates the upper limit on how many teams from a single nation are allowed to participate for each gender category.
-
D.
teamSizeFormat
Indicates how the size of a team is represented or formatted (e.g., as a number, range, or categorized label).
-
E.
teamCountType
Indicates how the number of teams is categorized or measured within a given context.
- 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_69f348ed74bc81909846aaa6a3c7318c |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6b0daa4988190b78498e7da6a30dd |
completed | May 3, 2026, 2:20 a.m. |
| PD | Predicate disambiguation | batch_69f6aca59d4881908d14ed47962703bd |
completed | May 3, 2026, 2:02 a.m. |
| PDg | Predicate description generation | batch_69f6af7d92008190aead47eaae8cc091 |
completed | May 3, 2026, 2:14 a.m. |
Created at: April 30, 2026, 11:57 p.m.