Triple
T29478195
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1920 South American Championship |
E747707
|
entity |
| Predicate | matchBallType |
P3186
|
FINISHED |
| Object | leather football |
—
|
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: leather football | Statement: [1920 South American Championship, matchBallType, leather football]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: matchBallType Context triple: [1920 South American Championship, matchBallType, leather football]
-
A.
matchBall
Indicates that an entity is associated with or participates in a particular ball used in a match or game.
-
B.
ballType
chosen
Indicates the specific category or kind of ball associated with an entity.
-
C.
ballOrObjectUsed
Indicates that a ball or other object is used as the instrument or tool in performing an action or event.
-
D.
ballName
Indicates that an entity has a specific name assigned to a ball.
-
E.
usesBallSport
Indicates that an activity or event involves the use of a ball as part of a sport.
- 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_69f66bd6e3b88190abb8dcb59d16767e |
completed | May 2, 2026, 9:25 p.m. |
| PD | Predicate disambiguation | batch_69f6659b62fc8190b21555d0ba54db2d |
completed | May 2, 2026, 8:59 p.m. |
Created at: April 28, 2026, 4:01 p.m.