Triple
T27298288
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Henry de Bromhead |
E688827
|
entity |
| Predicate | wonChampionHurdleWith |
P54773
|
FINISHED |
| Object | Honeysuckle |
—
|
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: Honeysuckle | Statement: [Henry de Bromhead, wonChampionHurdleWith, Honeysuckle]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wonChampionHurdleWith Context triple: [Henry de Bromhead, wonChampionHurdleWith, Honeysuckle]
-
A.
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).
-
B.
wonCheltenhamGoldCupWith
Indicates that an entity (typically a jockey, trainer, or owner) achieved victory in the Cheltenham Gold Cup using a particular horse.
-
C.
winnerLane
Indicates that a particular lane is the one in which the winner of a race or competition is located.
-
D.
competitionWonWith
chosen
Indicates that a competition was won using, involving, or in association with a particular participant, method, tool, or resource.
-
E.
winnerDam
Indicates that the subject entity is the dam (mother) of an offspring that has won a specified race or competition.
- 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_69f62cd2ceb481908cd9fae52a542206 |
completed | May 2, 2026, 4:56 p.m. |
| PD | Predicate disambiguation | batch_69f62c1762f881908c25e8f70ecd5041 |
completed | May 2, 2026, 4:53 p.m. |
Created at: April 27, 2026, 11:20 a.m.