Triple
T27545449
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Korea Football Association |
E695347
|
entity |
| Predicate | afcAffiliation |
P159893
|
FINISHED |
| Object | Asian Football Confederation |
—
|
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: Asian Football Confederation | Statement: [Korea Football Association, afcAffiliation, Asian Football Confederation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: afcAffiliation Context triple: [Korea Football Association, afcAffiliation, Asian Football Confederation]
-
A.
afcAffiliation
chosen
Indicates a formal association or membership relationship between an entity and an organization, group, or institution.
-
B.
leagueAffiliationOfTeam
Indicates that a sports team is affiliated with, or competes within, a particular league.
-
C.
team2Affiliation
Indicates that an entity is affiliated with, belongs to, or is associated with a second team in a given context.
-
D.
arenaFootballLeagueFranchiseId
Indicates that an entity is associated with a specific franchise identifier within the Arena Football League.
-
E.
playerAffiliation
Indicates the organization, team, or group with which a player is formally associated or aligned.
- 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_69ef5386c3e08190bfe33aa326e1f72b |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69f62f840a588190919f31170d31b0c9 |
completed | May 2, 2026, 5:08 p.m. |
| PD | Predicate disambiguation | batch_69f62c1762f881908c25e8f70ecd5041 |
completed | May 2, 2026, 4:53 p.m. |
Created at: April 27, 2026, 1:32 p.m.