Triple

T7261910
Position Surface form Disambiguated ID Type / Status
Subject Hamburg, South Carolina E159674 entity
Predicate legalPretextForAttack P63286 FINISHED
Object alleged obstruction of a public road by Black militia 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: alleged obstruction of a public road by Black militia | Statement: [Hamburg, South Carolina, legalPretextForAttack, alleged obstruction of a public road by Black militia]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: legalPretextForAttack
Context triple: [Hamburg, South Carolina, legalPretextForAttack, alleged obstruction of a public road by Black militia]
  • A. legalPretext chosen
    Indicates that an action or decision is justified using a stated legal reason that serves as a cover for a different, underlying motive.
  • B. eventUsedAsPretextFor
    Indicates that one event is cited or leveraged as a justification or excuse for carrying out another action or event.
  • C. legalActionReason
    Indicates the reason, cause, or grounds for which a particular legal action is initiated or taken.
  • D. pretext
    Indicates that one party uses a stated reason or excuse to conceal their true motive for an action or decision.
  • E. officeAttacked
    Indicates that an office was the target of an attack or violent action.
  • 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_69c68838f9948190875fd60b2351230c completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6eb088dac8190b353f6ea3d686025 completed March 27, 2026, 8:39 p.m.
PD Predicate disambiguation batch_69c6e76876608190ac4652bc7153302e completed March 27, 2026, 8:24 p.m.
Created at: March 27, 2026, 2:57 p.m.