Triple

T22690322
Position Surface form Disambiguated ID Type / Status
Subject CDK4 E561032 entity
Predicate conservedIn P25816 FINISHED
Object Mus musculus NE NERFINISHED

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: Mus musculus | Statement: [CDK4, conservedIn, Mus musculus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mus musculus
Context triple: [CDK4, conservedIn, Mus musculus]
  • A. Mus musculus castaneus
    Mus musculus castaneus is an Asian subspecies of the house mouse commonly used in genetic and evolutionary research.
  • B. house mouse (Mus musculus) chosen
    The house mouse (Mus musculus) is a small, globally distributed rodent that is one of the most important mammalian model organisms in biomedical and genetic research.
  • C. Rattus
    Rattus is a genus of rodents that includes several species of rats, many of which are widespread as commensal animals closely associated with human habitats.
  • D. Cavia porcellus
    Cavia porcellus, commonly known as the domestic guinea pig, is a small, tailless rodent widely kept as a household pet and used in scientific research.
  • E. Cavia aperea
    Cavia aperea is a wild South American rodent species closely related to the domestic guinea pig and commonly known as the Brazilian or common guinea pig.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e2454d71b48190a1f80af9f82b6fcf completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f1789a1fd08190bce5fa0babe695d3 completed April 29, 2026, 3:18 a.m.
Created at: April 17, 2026, 3:13 p.m.