Triple

T3194087
Position Surface form Disambiguated ID Type / Status
Subject Assemblée nationale E66893 entity
Predicate oversightPower P8878 FINISHED
Object parliamentary questions 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: parliamentary questions | Statement: [Assemblée nationale, oversightPower, parliamentary questions]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: oversightPower
Context triple: [Assemblée nationale, oversightPower, parliamentary questions]
  • A. oversightFocus
    Indicates that one entity’s oversight, supervision, or monitoring activities are specifically directed toward another entity or aspect.
  • B. oversightType
    Indicates the specific kind or category of oversight applied to an entity or activity, such as the manner or level of supervision, review, or regulatory control involved.
  • C. oversightScope
    Indicates the range or extent of responsibilities and activities that fall under an entity’s oversight or supervisory authority.
  • D. oversightBody chosen
    Indicates that one entity has formal authority to supervise, review, or regulate the actions or decisions of another entity.
  • E. oversightHistory
    Indicates the record of past supervisory or monitoring actions that have been applied to an entity over time.
  • 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_69ad8588ba18819086a10951c32ecb80 completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada714dbcc8190a7ad21b3c957f151 completed March 8, 2026, 4:43 p.m.
PD Predicate disambiguation batch_69ad9e05e4f48190adbe4366cdba2349 completed March 8, 2026, 4:04 p.m.
Created at: March 8, 2026, 3:07 p.m.