Triple
T25274250
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South Africa women's national football team |
E633651
|
entity |
| Predicate | bestFIFAWomensWorldCupResultYear |
P146765
|
FINISHED |
| Object | 2023 |
—
|
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 | Statement: [South Africa women's national football team, bestFIFAWomensWorldCupResultYear, 2023]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bestFIFAWomensWorldCupResultYear Context triple: [South Africa women's national football team, bestFIFAWomensWorldCupResultYear, 2023]
-
A.
bestUefaWomen’sChampionshipResult
Indicates the highest level of success an entity has achieved in the UEFA Women's Championship competition.
-
B.
FIFAWomen'sWorldCupAllTimeTopScorer
Indicates that the subject holds the record for scoring the most goals in the history of the FIFA Women's World Cup.
-
C.
bestResultFifaWWCYear
chosen
Indicates the year in which an entity achieved its best result in the FIFA Women’s World Cup.
-
D.
bestResultFifaU17WWCYear
Indicates the year in which an entity achieved its best performance or result at the FIFA U-17 Women's World Cup.
-
E.
BallonDorFeminineYearWon
Indicates the year in which a female player won the Ballon d'Or Féminin award.
- 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_69e75a92f48881909974ff9c11150a2e |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f48ba5024c8190acce739b3b97bdb8 |
completed | May 1, 2026, 11:16 a.m. |
| PD | Predicate disambiguation | batch_69f4683472ec8190a483b3b8afe71720 |
completed | May 1, 2026, 8:45 a.m. |
Created at: April 21, 2026, 1:17 p.m.