Triple
T26761737
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oxford University Swimming Club |
E674820
|
entity |
| Predicate | fieldOfCompetition |
P2440
|
FINISHED |
| Object | university swimming |
—
|
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: university swimming | Statement: [Oxford University Swimming Club, fieldOfCompetition, university swimming]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fieldOfCompetition Context triple: [Oxford University Swimming Club, fieldOfCompetition, university swimming]
-
A.
typeOfCompetition
chosen
Indicates the specific kind or category of competition in which an entity participates or is involved.
-
B.
competitionOf
Indicates a relationship where one entity is the competitive event, contest, or rivalry involving another entity.
-
C.
genreOfCompetition
Indicates the specific type or category of competition that an event or contest belongs to.
-
D.
competitionDepicted
Indicates that a competitive event or rivalry between entities is shown or represented in some medium or context.
-
E.
competitionEditionOf
Indicates that one entity is a specific edition or instance of a broader recurring competition or contest.
- 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_69f657f653448190a945b4751af8507d |
completed | May 2, 2026, 8 p.m. |
| PD | Predicate disambiguation | batch_69f6575ba12081909396036f78757a76 |
completed | May 2, 2026, 7:58 p.m. |
Created at: April 27, 2026, 3:58 a.m.