Triple

T5098244
Position Surface form Disambiguated ID Type / Status
Subject Michael Devine E114918 entity
Predicate associatedWithPrisonerProtest P56130 FINISHED
Object blanket protest 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: blanket protest | Statement: [Michael Devine, associatedWithPrisonerProtest, blanket protest]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: associatedWithPrisonerProtest
Context triple: [Michael Devine, associatedWithPrisonerProtest, blanket protest]
  • A. associatedWithPrisonProtest chosen
    Indicates a relationship where an entity is connected to, involved in, or linked with a protest occurring within or related to a prison context.
  • B. postPrisonOccupation
    Indicates the type of work or occupation a person engages in after being released from prison.
  • C. notableProtest
    Indicates that an entity is recognized for having led, organized, or been centrally involved in a significant protest or demonstration.
  • D. teamDuringProtest
    Indicates that two or more entities are part of the same team or organized group specifically in the context of a protest event.
  • E. hasPrisoners
    Indicates that an entity holds or contains one or more individuals who are imprisoned or detained.
  • 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_69bd443fc49c819089629c00e311310c completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd7567d21081909227ed8f08b74c71 completed March 20, 2026, 4:27 p.m.
PD Predicate disambiguation batch_69bd715e06808190931934dc9930f997 completed March 20, 2026, 4:10 p.m.
Created at: March 20, 2026, 1:40 p.m.