Triple

T7274266
Position Surface form Disambiguated ID Type / Status
Subject Geertje Dircx E162983 entity
Predicate relativeCertaintyOfModelAttribution P36359 FINISHED
Object disputed 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: disputed | Statement: [Geertje Dircx, relativeCertaintyOfModelAttribution, disputed]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: relativeCertaintyOfModelAttribution
Context triple: [Geertje Dircx, relativeCertaintyOfModelAttribution, disputed]
  • A. hasCertainty chosen
    Indicates that a statement, belief, or relationship is associated with a specific level or degree of confidence or surety.
  • B. requiresConfidenceOf
    Indicates that one entity can only proceed, function, or be accepted if it has sufficient trust, assurance, or belief in the reliability or correctness of another entity.
  • C. hasUncertainty
    Indicates that the relationship or value is associated with some level or type of uncertainty rather than being fully definite or precise.
  • D. trustModel
    Indicates that one entity relies on or has confidence in the reliability, integrity, or performance of another entity or system.
  • E. estimatedStrength
    Indicates that a value represents an approximate or inferred level, magnitude, or intensity of something rather than a precisely measured strength.
  • 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_69c6885c5964819085b209701769877f completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6eb8a0b4881908ff27c5a75bd4a95 completed March 27, 2026, 8:41 p.m.
PD Predicate disambiguation batch_69c6e76a84a081908d4184c55b728e48 completed March 27, 2026, 8:24 p.m.
Created at: March 27, 2026, 2:58 p.m.