Triple
T2713296
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South Africa national football team |
E59910
|
entity |
| Predicate | bestAFCONResult |
P14833
|
FINISHED |
| Object | champions |
—
|
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: champions | Statement: [South Africa national football team, bestAFCONResult, champions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bestAFCONResult Context triple: [South Africa national football team, bestAFCONResult, champions]
-
A.
wonAfricaCupOfNations
chosen
Indicates that the subject has won the Africa Cup of Nations football tournament.
-
B.
bestWorldCupResult
Indicates the most successful performance or highest achievement an entity has attained in any FIFA World Cup tournament.
-
C.
numberOfQualifiedTeamsFromAfrica
Indicates the count of teams from Africa that meet the specified qualification criteria.
-
D.
fifaU20WWC_bestResult
Indicates the best performance or highest stage a team has achieved in the FIFA U-20 Women's World Cup tournament.
-
E.
bestWorldCupResultYear
Indicates the year in which an entity achieved its best (highest) result in a World Cup tournament.
- 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_69ab4ac92a088190bc74bca14038e3de |
completed | March 6, 2026, 9:44 p.m. |
| NER | Named-entity recognition | batch_69abda924b24819090adc4128e86d4bd |
completed | March 7, 2026, 7:58 a.m. |
| PD | Predicate disambiguation | batch_69abd8224c688190bb4a362360b03007 |
completed | March 7, 2026, 7:47 a.m. |
Created at: March 6, 2026, 9:55 p.m.