Triple
T17662328
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Clearsky Farms |
E440282
|
entity |
| Predicate | horseTypeSpecialization |
P77266
|
FINISHED |
| Object | Thoroughbred |
—
|
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: Thoroughbred | Statement: [Clearsky Farms, horseTypeSpecialization, Thoroughbred]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: horseTypeSpecialization Context triple: [Clearsky Farms, horseTypeSpecialization, Thoroughbred]
-
A.
horseBreed
chosen
Indicates that one entity is a specific breed of the horse represented by the other entity.
-
B.
usesHorseType
Indicates that one entity employs, relies on, or operates using a specific type or category of horse.
-
C.
featuresHorse
Indicates that something includes, presents, or prominently involves a horse as a central element or subject.
-
D.
raceTypeDetail
Indicates the specific category or classification of a race, providing detailed information about the type of race involved in the relationship.
-
E.
ridingSpecialty
Indicates that one entity has a particular area of expertise or focus related to riding (e.g., a specific riding style, discipline, or type).
- 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_69d8b9e87e18819087104a44dc4dc5b1 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e46ea73c90819087a23a7b6171f581 |
completed | April 19, 2026, 5:56 a.m. |
| PD | Predicate disambiguation | batch_69e3cde007d8819090dd92eea9f022cc |
completed | April 18, 2026, 6:30 p.m. |
Created at: April 10, 2026, 9:48 a.m.