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.