Triple
T26762216
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oxford University Korfball Club |
E674834
|
entity |
| Predicate | playsMixedSport |
P155257
|
FINISHED |
| Object | korfball |
—
|
LITERAL FINISHED |
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: korfball | Statement: [Oxford University Korfball Club, playsMixedSport, korfball]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: playsMixedSport Context triple: [Oxford University Korfball Club, playsMixedSport, korfball]
-
A.
multiSport
Indicates that an entity participates in, is associated with, or is designed for more than one sport.
-
B.
sportsPlayed
chosen
Indicates that an entity participates in or engages in a particular sport.
-
C.
playsOutdoor
Indicates that an entity engages in an activity or game in an outdoor environment.
-
D.
competitiveGame
Indicates a relationship where entities participate in a game or contest in which they compete against each other to win or achieve a higher ranking.
-
E.
traditionalGame
Indicates that the relationship involves playing, practicing, or being associated with a game that is rooted in longstanding cultural or historical traditions.
- 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_69eecda85298819097ee1c38a3d772e7 |
completed | April 27, 2026, 2:44 a.m. |
| NER | Named-entity recognition | batch_69f6640168948190811bd5f933a87cf5 |
completed | May 2, 2026, 8:52 p.m. |
| PD | Predicate disambiguation | batch_69f6633451948190bcc0410602bb4914 |
completed | May 2, 2026, 8:48 p.m. |
Created at: April 27, 2026, 3:58 a.m.