Triple
T10455622
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kentucky horse culture |
E246544
|
entity |
| Predicate | includesBreed |
P41121
|
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: [Kentucky horse culture, includesBreed, Thoroughbred]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: includesBreed Context triple: [Kentucky horse culture, includesBreed, Thoroughbred]
-
A.
hasVarietyWithinBreed
Indicates that within a given breed, there exist distinct varieties or subtypes that are recognized as variations of that same breed.
-
B.
associatedAnimalBreed
chosen
Indicates that there is a relationship linking an entity to a specific breed of animal with which it is connected or identified.
-
C.
breedsIn
Indicates that an organism reproduces or carries out its breeding activities within a specified environment, habitat, or location.
-
D.
belongsToBreedGroup
Indicates that an animal is classified as a member of a specific breed group.
-
E.
breed
Indicates that an organism reproduces to generate offspring, typically with another organism of the same species.
- 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_69d381c04fe08190957c26c526a3b05a |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4fe48d15c8190bae0d4859e6cda5d |
completed | April 7, 2026, 12:53 p.m. |
| PD | Predicate disambiguation | batch_69d4fb7d353c8190a73f439a956c7606 |
completed | April 7, 2026, 12:41 p.m. |
Created at: April 6, 2026, 12:18 p.m.