Triple
T29478173
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1920 South American Championship |
E747707
|
entity |
| Predicate | currentTournamentName |
P41173
|
FINISHED |
| Object | Copa América |
—
|
NE NERFINISHED |
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: Copa América | Statement: [1920 South American Championship, currentTournamentName, Copa América]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: currentTournamentName Context triple: [1920 South American Championship, currentTournamentName, Copa América]
-
A.
currentNameOfCompetition
chosen
Indicates that an entity is the present, official name by which a particular competition is currently known.
-
B.
currentCompetition
Indicates that two or more entities are presently engaged in the same ongoing competition or contest.
-
C.
latestTournamentAsOf2023
Indicates that the referenced tournament is the most recent one that occurred on or before the year 2023.
-
D.
nextTournament
Indicates that one entity is the immediately upcoming tournament scheduled to occur for the other entity.
-
E.
otherTournament
Indicates a relationship where one tournament is distinct from and not the same as another 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_69f0bd42cf308190bb01b20bc5b7c2d0 |
completed | April 28, 2026, 1:59 p.m. |
| NER | Named-entity recognition | batch_69fd553d7cb881908d243e7a9f30ac85 |
completed | May 8, 2026, 3:15 a.m. |
| PD | Predicate disambiguation | batch_69fd514dcb1c81908333c70d7edd79c9 |
completed | May 8, 2026, 2:58 a.m. |
Created at: April 28, 2026, 4:01 p.m.