Triple
T27688177
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | AFC competitions |
E698087
|
entity |
| Predicate | topClubTournament |
P93362
|
FINISHED |
| Object | AFC Champions League |
—
|
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: AFC Champions League | Statement: [AFC competitions, topClubTournament, AFC Champions League]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: topClubTournament Context triple: [AFC competitions, topClubTournament, AFC Champions League]
-
A.
primaryClubTournament
chosen
Indicates the main club-level tournament or competition in which an entity (typically a sports club or team) primarily participates or is most prominently associated.
-
B.
topClubsParticipateIn
Indicates that leading or highest-ranked clubs take part in a specified event, competition, or activity.
-
C.
homeTournament
Indicates that a tournament is being held at or hosted by the referenced entity’s home venue or location.
-
D.
tournamentsAward
Indicates that a tournament grants or confers a specific award or prize to an entity.
-
E.
primaryTournament
Indicates that a given tournament is the main or most important competition associated with an entity (such as a player, team, or season).
- 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_69ef590df8708190af5488f0638e790c |
completed | April 27, 2026, 12:39 p.m. |
| NER | Named-entity recognition | batch_69f63574d2388190839cd1061e3c9074 |
completed | May 2, 2026, 5:33 p.m. |
| PD | Predicate disambiguation | batch_69f62c1a92648190835a2c5250d8c758 |
completed | May 2, 2026, 4:53 p.m. |
Created at: April 27, 2026, 2:50 p.m.