Triple
T27143700
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mares’ Hurdle |
E681881
|
entity |
| Predicate | recordTrainerWinsHolder |
P7620
|
FINISHED |
| Object | Willie Mullins |
—
|
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: Willie Mullins | Statement: [Mares’ Hurdle, recordTrainerWinsHolder, Willie Mullins]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: recordTrainerWinsHolder Context triple: [Mares’ Hurdle, recordTrainerWinsHolder, Willie Mullins]
-
A.
winningTrainer
Indicates that the trainer is the one who achieved victory in a particular competition or event.
-
B.
managerialRecordWins
Indicates the number of wins credited to an individual in their role as a manager or head coach.
-
C.
mostSuccessfulTrainer
Indicates that the subject is the trainer who has achieved the highest level of success (e.g., by wins, titles, or performance metrics) among a given set of trainers.
-
D.
mostOverallWinsRecord
chosen
Indicates that the subject holds the record for having the greatest total number of wins compared to all others in the relevant context.
-
E.
raceRecordWins
Indicates that one entity has achieved a greater number of wins than another entity in recorded races.
- 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_69eefacca3888190b67238d380e8f28b |
completed | April 27, 2026, 5:57 a.m. |
| NER | Named-entity recognition | batch_69f6aaf50be08190a2b62a6d881f8aee |
completed | May 3, 2026, 1:55 a.m. |
| PD | Predicate disambiguation | batch_69f6aa1c555081908787dbf76147f180 |
completed | May 3, 2026, 1:51 a.m. |
Created at: April 27, 2026, 9:10 a.m.