Triple
T29126111
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oran Kearney |
E738232
|
entity |
| Predicate | clubServedAsPlayer |
P2170
|
FINISHED |
| Object | Ballymena United F.C. |
—
|
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: Ballymena United F.C. | Statement: [Oran Kearney, clubServedAsPlayer, Ballymena United F.C.]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: clubServedAsPlayer Context triple: [Oran Kearney, clubServedAsPlayer, Ballymena United F.C.]
-
A.
leagueParticipatedInAsPlayer
Indicates that a person, in the role of a player, took part in competitions organized by a specific league.
-
B.
memberTeamAtVariousTimes
Indicates that an entity has been a member of a particular team during one or more distinct time periods.
-
C.
representedClub
Indicates that an entity has acted as a representative of, or played for, a particular club or team.
-
D.
associatedClubBeganPlay
Indicates that the related club began its competitive play or official participation at the specified time.
-
E.
playedFor
chosen
Indicates that one entity has been a member of or participated as a player for a particular team, organization, or group.
- 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_69f07cb29cdc8190afa55444553de60c |
completed | April 28, 2026, 9:24 a.m. |
| NER | Named-entity recognition | batch_69f6622a39d48190b2e3bda35831060a |
completed | May 2, 2026, 8:44 p.m. |
| PD | Predicate disambiguation | batch_69f65c2376a08190be5215171e908e69 |
completed | May 2, 2026, 8:18 p.m. |
Created at: April 28, 2026, 11:28 a.m.