Triple
T34925685
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kevin-Prince Boateng |
E1007275
|
entity |
| Predicate | majorClub |
P20312
|
FINISHED |
| Object | A.C. Milan |
—
|
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: A.C. Milan | Statement: [Kevin-Prince Boateng, majorClub, A.C. Milan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: majorClub Context triple: [Kevin-Prince Boateng, majorClub, A.C. Milan]
-
A.
majorLeagueParentClub
Indicates that one sports club serves as the primary or top-tier (major league) affiliate or parent organization of another club.
-
B.
majorTeam
chosen
Indicates that one entity is the primary or most significant team associated with another entity (such as a person, event, or organization).
-
C.
notableClub
Indicates that an entity is prominently associated with or recognized for membership in a particular club or organization.
-
D.
otherProminentClub
Indicates a relationship where an entity is associated with another club that is also notable or high-profile, distinct from its primary or main club.
-
E.
topClubsParticipateIn
Indicates that leading or highest-ranked clubs take part in a specified event, competition, or activity.
- 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_69f76dc3d83881909d5c3c14455cfa2c |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69ff7595c9bc8190982c6e6e07a0c78f |
completed | May 9, 2026, 5:57 p.m. |
| PD | Predicate disambiguation | batch_69ff715432a88190a25670d26614bde2 |
completed | May 9, 2026, 5:39 p.m. |
Created at: May 3, 2026, 4 p.m.