Triple

T16211659
Position Surface form Disambiguated ID Type / Status
Subject Hirudo medicinalis E393479 entity
Predicate approvedMedicalUse P40313 FINISHED
Object adjunct therapy in plastic surgery 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: adjunct therapy in plastic surgery | Statement: [Hirudo medicinalis, approvedMedicalUse, adjunct therapy in plastic surgery]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: approvedMedicalUse
Context triple: [Hirudo medicinalis, approvedMedicalUse, adjunct therapy in plastic surgery]
  • A. medicinalUse chosen
    Indicates that one entity is used as a treatment or remedy for a disease, condition, or health-related purpose affecting another entity.
  • B. approvedDrugForm
    Indicates that a particular pharmaceutical form (e.g., tablet, injection) is an officially approved formulation of a given drug.
  • C. potentialTherapeuticUse
    Indicates that something is being considered or investigated as a possible treatment or therapy for a condition or disease.
  • D. approvedPractice
    Indicates that a particular practice, method, or procedure has been formally reviewed and granted official approval for use or adoption.
  • E. eligibleUses
    Indicates the types of actions, purposes, or contexts in which something is permitted or qualified to be used.
  • 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_69d87f1f5bd08190bd01cac0d5b9d2ef completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e227f1bef8819094e724f5cd0b86d5 completed April 17, 2026, 12:30 p.m.
PD Predicate disambiguation batch_69e219e94a448190b73a4e6aa374eb4a completed April 17, 2026, 11:30 a.m.
Created at: April 10, 2026, 5:03 a.m.