Triple

T23186762
Position Surface form Disambiguated ID Type / Status
Subject Kevzara E579611 entity
Predicate monoclonalAntibodyType P134655 FINISHED
Object human monoclonal antibody 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: human monoclonal antibody | Statement: [Kevzara, monoclonalAntibodyType, human monoclonal antibody]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: monoclonalAntibodyType
Context triple: [Kevzara, monoclonalAntibodyType, human monoclonal antibody]
  • A. antibodyType
    Indicates the specific class or subtype of an antibody involved in the described relationship or context.
  • B. isHumanMonoclonalAntibody chosen
    Indicates that the entity is a monoclonal antibody derived from human immune cells or engineered to have fully human antibody sequences.
  • C. associatedWithAntibody
    Indicates a relationship where something is linked or connected to a specific antibody, such as being produced by it, targeted by it, or otherwise functionally related to it.
  • D. basedOnAntibody
    Indicates that something is derived from, developed using, or fundamentally dependent on a specific antibody.
  • E. impactOnMonoclonalAntibodies
    Indicates the effect that something has on the behavior, efficacy, or properties of monoclonal antibodies.
  • 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_69e245ff8000819090d12008805315b7 completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f18fd3aaa08190b9cf7afe4ee5a38d completed April 29, 2026, 4:57 a.m.
PD Predicate disambiguation batch_69ef8a041c0081909afb670d17a5aaba completed April 27, 2026, 4:08 p.m.
Created at: April 17, 2026, 4:05 p.m.