Triple

T449648
Position Surface form Disambiguated ID Type / Status
Subject Office of Research and Development E7097 entity
Predicate governsBy P1051 FINISHED
Object research policies 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: research policies | Statement: [Office of Research and Development, governsBy, research policies]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: governsBy
Context triple: [Office of Research and Development, governsBy, research policies]
  • A. governs
    Indicates that one entity exercises authoritative control, direction, or rule over another entity or domain.
  • B. governedAs
    Indicates that one entity exercises authoritative control, direction, or rule over another according to some system of governance or leadership.
  • C. governedFrom
    Indicates that an entity exercises governing authority or administrative control over another entity from a specific location or seat of power.
  • D. governingPolicy chosen
    Indicates that one entity serves as the authoritative policy or set of rules that directs, constrains, or regulates the behavior, operation, or decisions of another entity.
  • E. governedByLegalRegime
    Indicates that an entity is subject to, regulated by, or operating under a specific legal framework or set of legal rules.
  • 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_69a2e7e4676c81909ea0dbdecac0687c completed Feb. 28, 2026, 1:04 p.m.
NER Named-entity recognition batch_69a2ef691cc8819091729eaac52c9457 completed Feb. 28, 2026, 1:36 p.m.
PD Predicate disambiguation batch_69a2ede1a1108190a4a06b3416ae6156 completed Feb. 28, 2026, 1:30 p.m.
Created at: Feb. 28, 2026, 1:12 p.m.