Triple

T4579339
Position Surface form Disambiguated ID Type / Status
Subject Permanent Record E101814 entity
Predicate subjectOfLegalAction P3996 FINISHED
Object United States Department of Justice civil lawsuit 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: United States Department of Justice civil lawsuit | Statement: [Permanent Record, subjectOfLegalAction, United States Department of Justice civil lawsuit]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: subjectOfLegalAction
Context triple: [Permanent Record, subjectOfLegalAction, United States Department of Justice civil lawsuit]
  • A. subjectOfProsecution
    Indicates that an entity is the target or focus of a legal prosecution or criminal proceeding initiated by an authority.
  • B. legalCase chosen
    Indicates a relationship where a formal legal dispute or proceeding exists between parties, typically adjudicated by a court or similar authority.
  • C. legalSubject
    Indicates that an entity is the bearer of legal rights, duties, or responsibilities within a legal relationship or context.
  • D. litigationType
    Indicates the specific category or nature of a legal dispute or court case associated with an entity or event.
  • E. disputeInvolves
    Indicates that a particular dispute includes or concerns the specified entities as participants or parties to the conflict.
  • 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_69bd43d4ce208190b53158c882b222e3 completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd58e3e028819083c4662deb9f3c03 completed March 20, 2026, 2:25 p.m.
PD Predicate disambiguation batch_69bd5228b70c8190ac48705e35a710c1 completed March 20, 2026, 1:56 p.m.
Created at: March 20, 2026, 1:10 p.m.