Triple

T37980220
Position Surface form Disambiguated ID Type / Status
Subject Viktor Bout E947530 entity
Predicate allegedFormerAffiliation P1168 FINISHED
Object Soviet Air Force 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: Soviet Air Force | Statement: [Viktor Bout, allegedFormerAffiliation, Soviet Air Force]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: allegedFormerAffiliation
Context triple: [Viktor Bout, allegedFormerAffiliation, Soviet Air Force]
  • A. formerAdministrativeAffiliation
    Indicates that an entity used to be administratively affiliated with another entity in the past, but that affiliation no longer holds.
  • B. formerMemberOf chosen
    Indicates that an entity once belonged to or was affiliated with a group, organization, or body, but is no longer a member.
  • C. formerAffiliationLevel
    Indicates that an entity previously held a specific level or status within an affiliation, but no longer does so.
  • D. previousCorporateAffiliation
    Indicates that an entity was formerly employed by, associated with, or part of a specified corporate organization before its current status or affiliation.
  • E. possibleAffiliation
    Indicates that there is a potential or uncertain organizational, group, or institutional association between the entities, but the affiliation is not confirmed.
  • 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_69f76ef8a1d08190a741bbbc5970e3b3 completed May 3, 2026, 3:51 p.m.
NER Named-entity recognition batch_69fcef654d588190b29ecc76678d1aa0 completed May 7, 2026, 8 p.m.
PD Predicate disambiguation batch_69fcecdb97f48190b382b7d13be92dc0 completed May 7, 2026, 7:49 p.m.
Created at: May 3, 2026, 4:20 p.m.