Triple
T16515156
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New York Racing Association |
E401162
|
entity |
| Predicate | hasPrimaryAnimal |
P13551
|
FINISHED |
| Object | Thoroughbred horse |
—
|
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 horse | Statement: [New York Racing Association, hasPrimaryAnimal, Thoroughbred horse]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPrimaryAnimal Context triple: [New York Racing Association, hasPrimaryAnimal, Thoroughbred horse]
-
A.
hasAnimal
chosen
Indicates that one entity possesses, keeps, or is associated with an animal.
-
B.
hasAnimalActor
Indicates that an animal serves as the acting agent or performer in the specified event or relationship.
-
C.
hasAnimalClass
Indicates that an entity belongs to, or is categorized under, a particular animal class (such as mammal, bird, reptile, etc.).
-
D.
hasAnimalCollection
Indicates that one entity possesses or maintains a collection or group of animals associated with it.
-
E.
hasCamelSpecies
Indicates that one entity is a camel and the other specifies the biological species to which that camel belongs.
- 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_69d883838abc8190bc79cb2d41733ce2 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e32e7bbfa481909037148cdb4d8996 |
completed | April 18, 2026, 7:10 a.m. |
| PD | Predicate disambiguation | batch_69e296995d388190b88ebe189dce890d |
completed | April 17, 2026, 8:22 p.m. |
Created at: April 10, 2026, 5:14 a.m.