Triple
T27298287
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Henry de Bromhead |
E688827
|
entity |
| Predicate | wonCheltenhamGoldCupWith |
P162315
|
FINISHED |
| Object | A Plus Tard |
—
|
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: A Plus Tard | Statement: [Henry de Bromhead, wonCheltenhamGoldCupWith, A Plus Tard]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wonCheltenhamGoldCupWith Context triple: [Henry de Bromhead, wonCheltenhamGoldCupWith, A Plus Tard]
-
A.
wonCheltenhamGoldCupWith
chosen
Indicates that an entity (typically a jockey, trainer, or owner) achieved victory in the Cheltenham Gold Cup using a particular horse.
-
B.
wonGrandNationalWith
Indicates that one entity achieved victory in the Grand National event using or in association with another entity (such as a horse, team, or participant).
-
C.
numberOfWinsInBetfairChase
Indicates how many times an entity has won the Betfair Chase race.
-
D.
numberOfWinsInKingGeorgeVIChase
Indicates the number of times an entity has won the King George VI Chase race.
-
E.
breedersCupWin
Indicates that an entity has achieved a victory in a Breeders' Cup race.
- 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_69ef355a96308190a2bed991525fb278 |
completed | April 27, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69f62782b9048190b942a03b3518b863 |
completed | May 2, 2026, 4:34 p.m. |
| PD | Predicate disambiguation | batch_69f623a91b9c8190b2e2fdbc55cb89b6 |
completed | May 2, 2026, 4:17 p.m. |
Created at: April 27, 2026, 11:20 a.m.