Triple

T7863096
Position Surface form Disambiguated ID Type / Status
Subject Troop U E182547 entity
Predicate policeFunction P61008 FINISHED
Object patrol 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: patrol | Statement: [Troop U, policeFunction, patrol]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: policeFunction
Context triple: [Troop U, policeFunction, patrol]
  • A. lawEnforcementFunction chosen
    Indicates that an entity performs, is responsible for, or is associated with official law enforcement duties or activities.
  • B. policeSystem
    Indicates a relationship where an entity functions as, belongs to, or is governed by a system of law enforcement or policing.
  • C. policeControl
    Indicates that one entity exercises authoritative oversight, regulation, or enforcement power over another, as a police force does over people or areas under its jurisdiction.
  • D. policeBureau
    Indicates that an entity functions as or is associated with a police bureau or police department.
  • E. policeNumber
    Indicates that an entity is associated with a specific police-related identification or reference number.
  • 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_69ca82887fd48190975896bf38c4596b completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cb36bfd8a4819093c2ef6d47891a68 completed March 31, 2026, 2:51 a.m.
PD Predicate disambiguation batch_69cae925ca388190ae4a01fa76e957e8 completed March 30, 2026, 9:20 p.m.
Created at: March 30, 2026, 4:54 p.m.