Triple

T19838991
Position Surface form Disambiguated ID Type / Status
Subject Assembly of the Republic plenary E476672 entity
Predicate mainActivityType P20949 FINISHED
Object legislative debates 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: legislative debates | Statement: [Assembly of the Republic plenary, mainActivityType, legislative debates]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: mainActivityType
Context triple: [Assembly of the Republic plenary, mainActivityType, legislative debates]
  • A. majorActivity
    Indicates that the related entity performs, participates in, or is primarily associated with a main or most significant activity.
  • B. hasActivityType chosen
    Indicates the specific kind or category of activity associated with an entity or event.
  • C. mainPresenter
    Indicates that one entity serves as the primary or lead presenter for another entity, such as an event, program, or presentation.
  • D. mainCurrentAct
    Indicates that an entity is currently performing or engaged in its primary or most important action or activity.
  • E. mainContentType
    Indicates the primary type or category of content associated with an entity or resource.
  • 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_69d8e51d39d081909bcfafeaaf3d2fcc completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65803bb988190a4e7c0035058feba completed April 20, 2026, 4:44 p.m.
PD Predicate disambiguation batch_69e5305bda388190a23b7191768107b1 completed April 19, 2026, 7:43 p.m.
Created at: April 10, 2026, 1:50 p.m.