Triple

T36506988
Position Surface form Disambiguated ID Type / Status
Subject Lori Fortier E899492 entity
Predicate notableCourtRole P23470 FINISHED
Object government witness for the 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: government witness for the prosecution | Statement: [Lori Fortier, notableCourtRole, government witness for the prosecution]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: notableCourtRole
Context triple: [Lori Fortier, notableCourtRole, government witness for the prosecution]
  • A. notableCourt
    Indicates that a particular court is especially significant or noteworthy in relation to the subject.
  • B. courtRole chosen
    Indicates the specific capacity or position an entity holds within a court proceeding or judicial context.
  • C. judicialRole
    Indicates that one entity holds or performs a specific official function or position within the judicial system in relation to another entity or legal matter.
  • D. notableOfficerRole
    Indicates that an entity holds or has held a particularly significant or distinguished officer position within an organization or institution.
  • E. notableHolderRole
    Indicates that an entity is recognized for holding a particular role, office, or position in a notable or distinguished capacity.
  • 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_69f76e5b92088190933afda3f7531dd4 completed May 3, 2026, 3:48 p.m.
NER Named-entity recognition batch_6a037c8e2c648190a65fc9c7872861af completed May 12, 2026, 7:16 p.m.
PD Predicate disambiguation batch_6a037a0bf4b88190bdcfae9a14b51f0a completed May 12, 2026, 7:05 p.m.
Created at: May 3, 2026, 4:10 p.m.