Triple
T15300287
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Novosibirsk Zoo |
E365766
|
entity |
| Predicate | hasBreedingProgramFor |
P55482
|
FINISHED |
| Object | snow leopard |
—
|
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: snow leopard | Statement: [Novosibirsk Zoo, hasBreedingProgramFor, snow leopard]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasBreedingProgramFor Context triple: [Novosibirsk Zoo, hasBreedingProgramFor, snow leopard]
-
A.
hasBreedingProgram
chosen
Indicates that an entity operates, participates in, or maintains an organized program for breeding organisms (such as animals or plants).
-
B.
breedingInstitutionType
Indicates the type or category of institution responsible for breeding organisms or animals.
-
C.
breedingGoal
Indicates that one entity is the intended objective or target outcome of a breeding process involving another entity.
-
D.
hasBreedingCode
Indicates that an entity is associated with a specific code representing its breeding status, behavior, or category.
-
E.
breeder
Indicates that an entity is responsible for producing, raising, or propagating another entity, typically through controlled reproduction.
- 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_69d85a113ee881908e297a1d38dd79fa |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e0368869f8819098cf9e7801e37548 |
completed | April 16, 2026, 1:08 a.m. |
| PD | Predicate disambiguation | batch_69deca935e2c8190b640987ddfc542b9 |
completed | April 14, 2026, 11:15 p.m. |
Created at: April 10, 2026, 3:15 a.m.