Triple
T27231412
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Durkan Memorial Chase |
E682163
|
entity |
| Predicate | notableJockeyAssociated |
P55480
|
FINISHED |
| Object | Ruby Walsh |
—
|
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: Ruby Walsh | Statement: [John Durkan Memorial Chase, notableJockeyAssociated, Ruby Walsh]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableJockeyAssociated Context triple: [John Durkan Memorial Chase, notableJockeyAssociated, Ruby Walsh]
-
A.
hasNotableJockey
chosen
Indicates that an entity (typically a racehorse) is or was ridden by a jockey who is considered notable or distinguished.
-
B.
mostSuccessfulJockey
Indicates that the subject is the jockey with the highest level of success (e.g., most wins or top performance) in a given context or competition.
-
C.
notableHorse
Indicates that the subject is a horse recognized for particular significance, fame, or distinction.
-
D.
notableRacingSuccess
Indicates that the subject has achieved significant or distinguished success in competitive racing events.
-
E.
hasJockey
Indicates that a racehorse is associated with or ridden by a particular jockey.
- 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_69eefacdad7881908b7bca61c90a1a1e |
completed | April 27, 2026, 5:57 a.m. |
| NER | Named-entity recognition | batch_69ffac35ac5481908b6bdfd5bbe8c76e |
completed | May 9, 2026, 9:50 p.m. |
| PD | Predicate disambiguation | batch_69ffabbfd2548190964c851496bbbaee |
completed | May 9, 2026, 9:48 p.m. |
Created at: April 27, 2026, 9:46 a.m.