Triple

T20058044
Position Surface form Disambiguated ID Type / Status
Subject Queipo de Llano E499391 entity
Predicate targetOfRepression P40675 FINISHED
Object Republican supporters 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: Republican supporters | Statement: [Queipo de Llano, targetOfRepression, Republican supporters]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: targetOfRepression
Context triple: [Queipo de Llano, targetOfRepression, Republican supporters]
  • A. notableRepressionEvent
    Indicates a significant instance in which an entity engaged in or experienced systematic repression, such as suppression of rights, freedoms, or dissent.
  • B. perpetratorsTargeted
    Indicates that the perpetrators intentionally selected or focused on specific targets for their actions.
  • C. oppositionTargeted chosen
    Indicates that an action or strategy is specifically directed against or aimed at an opposing party, group, or viewpoint.
  • D. repressedDissent
    Indicates that one party has actively suppressed or stifled opposition, criticism, or disagreement from another party or group.
  • E. associatedWithRepressionSystem
    Indicates that an entity is connected to, involved in, or part of a system or mechanism used for repression or suppressive control.
  • 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_69da6276bcf48190aabbf279192a5fb4 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e6637325908190aefc0e27e2ed5750 completed April 20, 2026, 5:33 p.m.
PD Predicate disambiguation batch_69e54cee7a5c819084ae4ff26419833f completed April 19, 2026, 9:45 p.m.
Created at: April 11, 2026, 3:38 p.m.