Triple
T18318805
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Native Trail |
E438815
|
entity |
| Predicate | raceClassOfIrish2000Guineas |
P49218
|
FINISHED |
| Object | Group 1 |
—
|
LITERAL FINISHED |
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: Group 1 | Statement: [Native Trail, raceClassOfIrish2000Guineas, Group 1]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: raceClassOfIrish2000Guineas Context triple: [Native Trail, raceClassOfIrish2000Guineas, Group 1]
-
A.
racecourseType
Indicates the specific kind or classification of a racecourse associated with an entity.
-
B.
nationalityAsRacehorse
Indicates the country or region with which a racehorse is officially associated or registered for racing purposes.
-
C.
raceTypeDetail
chosen
Indicates the specific category or classification of a race, providing detailed information about the type of race involved in the relationship.
-
D.
leadingSireInGreatBritain
Indicates that a male horse was the most successful sire in Great Britain for a given period, typically based on the racing performance or earnings of its offspring.
-
E.
horseOfTheYearCampaignFor
Indicates that an entity conducted or was involved in a campaign promoting a particular horse for a Horse of the Year title or award.
- 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_69d8b916a2d081909e249e4902f6aad9 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e50aa342a881909afcd995405027af |
completed | April 19, 2026, 5:02 p.m. |
| PD | Predicate disambiguation | batch_69e44fe4ee10819086b4142444fca1f5 |
completed | April 19, 2026, 3:45 a.m. |
Created at: April 10, 2026, 10:36 a.m.