Triple

T460259
Position Surface form Disambiguated ID Type / Status
Subject Assistant United States Attorney E7320 entity
Predicate maySpecializeIn P466 FINISHED
Object criminal prosecution 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: criminal prosecution | Statement: [Assistant United States Attorney, maySpecializeIn, criminal prosecution]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: maySpecializeIn
Context triple: [Assistant United States Attorney, maySpecializeIn, criminal prosecution]
  • A. hasSpecialty chosen
    Indicates that an entity possesses a particular area of expertise, focus, or professional specialization.
  • B. specialCaseOf
    Indicates that one entity represents a more specific, exceptional, or restricted instance of the general situation, rule, or relationship expressed by another entity.
  • C. canAlsoBe
    Indicates that something has an additional possible state, role, or classification beyond its primary one.
  • D. mayExtendTo
    Indicates that something has the potential or permission to reach, continue, or be applied up to a specified limit, scope, or boundary.
  • E. subDisciplineOf
    Indicates that one discipline is a more specialized or narrower field within another, broader discipline.
  • 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_69a2e7e5c5bc8190a1dc8178218fba40 completed Feb. 28, 2026, 1:04 p.m.
NER Named-entity recognition batch_69a2efbd6ed481909ec40f12b5b675c8 completed Feb. 28, 2026, 1:38 p.m.
PD Predicate disambiguation batch_69a2ede75b6c81908350103d21f22a03 completed Feb. 28, 2026, 1:30 p.m.
Created at: Feb. 28, 2026, 1:12 p.m.