Triple

T26778659
Position Surface form Disambiguated ID Type / Status
Subject Trump–Ukraine scandal E670189 entity
Predicate allegedTargetOfPressure P165366 FINISHED
Object Volodymyr Zelenskyy 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: Volodymyr Zelenskyy | Statement: [Trump–Ukraine scandal, allegedTargetOfPressure, Volodymyr Zelenskyy]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: allegedTargetOfPressure
Context triple: [Trump–Ukraine scandal, allegedTargetOfPressure, Volodymyr Zelenskyy]
  • A. politicalPressureFrom
    Indicates that one entity is exerting political influence or coercion on another to shape decisions, actions, or policies.
  • B. oppositionTargeted
    Indicates that an action or strategy is specifically directed against or aimed at an opposing party, group, or viewpoint.
  • C. allegedAgentOf
    Indicates that one entity is claimed or suspected, but not confirmed, to be the agent responsible for an action or event involving another entity.
  • D. usesLegalPressureOn
    Indicates that one party applies legal mechanisms, such as lawsuits or regulatory actions, to compel, influence, or coerce another party.
  • E. allegedTargetGroup
    Indicates that a group is claimed or suspected to be the intended target of an action, plan, or attack, without confirming that the claim is true.
  • F. None of above. chosen

Provenance (4 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_69eeb31c925881909b597f6e40056d28 completed April 27, 2026, 12:51 a.m.
NER Named-entity recognition batch_69f658a91ba0819084fbe3dd8a09f7cd completed May 2, 2026, 8:03 p.m.
PD Predicate disambiguation batch_69f6575ba12081909396036f78757a76 completed May 2, 2026, 7:58 p.m.
PDg Predicate description generation batch_69f657f2c8b08190bfeb3173ef78207d completed May 2, 2026, 8 p.m.
Created at: April 27, 2026, 4:07 a.m.