Triple
T31378156
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Franck Kessié |
E800367
|
entity |
| Predicate | playedInTournamentFor |
P10753
|
FINISHED |
| Object | Ivory Coast at Africa Cup of Nations |
—
|
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: Ivory Coast at Africa Cup of Nations | Statement: [Franck Kessié, playedInTournamentFor, Ivory Coast at Africa Cup of Nations]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: playedInTournamentFor Context triple: [Franck Kessié, playedInTournamentFor, Ivory Coast at Africa Cup of Nations]
-
A.
playedInTournament
chosen
Indicates that an entity participated as a competitor or player in a specific tournament.
-
B.
scoredInTournament
Indicates that an entity achieved a score or points during a particular tournament.
-
C.
usedInTournamentDraws
Indicates that something (such as a rule, method, or system) is employed when constructing or organizing the draws for a tournament.
-
D.
hasTournamentRecord
Indicates that an entity possesses a documented performance or results record in a specific tournament or set of tournaments.
-
E.
playInTournamentIntroduced
Indicates that an entity participates as a player in a specific tournament that has been newly introduced or added.
- 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_69f224e84da08190abfc2f17494a33c8 |
completed | April 29, 2026, 3:34 p.m. |
| NER | Named-entity recognition | batch_69f7764ab1fc81909f9348db87bd7692 |
completed | May 3, 2026, 4:22 p.m. |
| PD | Predicate disambiguation | batch_69f76905d9c88190b1ee810bc9ab644f |
completed | May 3, 2026, 3:25 p.m. |
Created at: April 29, 2026, 9:18 p.m.