Triple

T29902646
Position Surface form Disambiguated ID Type / Status
Subject Office of Victim Services (Maine Department of Corrections) E759450 entity
Predicate processScope P89488 FINISHED
Object correctional process 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: correctional process | Statement: [Office of Victim Services (Maine Department of Corrections), processScope, correctional process]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: processScope
Context triple: [Office of Victim Services (Maine Department of Corrections), processScope, correctional process]
  • A. programmaticScope chosen
    Indicates the defined range or boundary within which a program, initiative, or set of actions is intended to operate or have effect.
  • B. componentScope
    Indicates that one entity defines or constrains the scope, visibility, or applicability of another component within a system or context.
  • C. sessionScope
    Indicates that a variable, resource, or configuration is associated with and persists for the duration of a single user session.
  • D. participantScope
    Indicates the extent, range, or set of participants that are involved in or affected by a given relationship or action.
  • E. laterScope
    Indicates that one event, state, or condition occurs or applies after the temporal scope of another.
  • 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_69f224600590819085e148a01c056ef6 completed April 29, 2026, 3:31 p.m.
NER Named-entity recognition batch_69f6772fce348190bc69daffad2fc0f1 completed May 2, 2026, 10:14 p.m.
PD Predicate disambiguation batch_69f675ff62c48190a634bbb8896973b9 completed May 2, 2026, 10:09 p.m.
Created at: April 29, 2026, 6:07 p.m.