Triple

T4784852
Position Surface form Disambiguated ID Type / Status
Subject 2017 Équateur Province Ebola outbreak E106450 entity
Predicate laboratoryConfirmation P19381 FINISHED
Object Ebola virus detected by PCR 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: Ebola virus detected by PCR | Statement: [2017 Équateur Province Ebola outbreak, laboratoryConfirmation, Ebola virus detected by PCR]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: laboratoryConfirmation
Context triple: [2017 Équateur Province Ebola outbreak, laboratoryConfirmation, Ebola virus detected by PCR]
  • A. laboratoryModule
    Indicates a relationship where an entity is a laboratory module or functions as a lab-specific component or unit within a larger system or structure.
  • B. laboratoryMedium
    Indicates that one entity serves as the culture or growth medium used in a laboratory context for another entity.
  • C. affectsLaboratoryTest
    Indicates that one entity has an influence on, alters, or changes the outcome, value, or interpretation of a laboratory test.
  • D. confirmedFinding chosen
    Indicates that a finding or observation has been verified as true or accurate, rather than being tentative or suspected.
  • E. judgeConfirmationBy
    Indicates that one entity evaluates and validates another entity or action according to certain criteria or standards.
  • 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_69bd43f4a9588190bf73e20bc27c03cc completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd65ae49ec81908f16248d22d1155f completed March 20, 2026, 3:20 p.m.
PD Predicate disambiguation batch_69bd622e1b408190806c15c61519fc74 completed March 20, 2026, 3:05 p.m.
Created at: March 20, 2026, 1:22 p.m.