Triple

T5460926
Position Surface form Disambiguated ID Type / Status
Subject Brazilian government E122590 entity
Predicate electoralSystemPresidential P539 FINISHED
Object two-round system 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: two-round system | Statement: [Brazilian government, electoralSystemPresidential, two-round system]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: electoralSystemPresidential
Context triple: [Brazilian government, electoralSystemPresidential, two-round system]
  • A. presidencySelection
    Indicates the process or outcome by which an individual is chosen or appointed to hold the office of the presidency.
  • B. electoralSystemForLegislature
    Indicates the type of electoral system used to choose members of a particular legislature.
  • C. electoralSystemContext
    Indicates the electoral system or framework within which a political or electoral event, action, or relationship takes place.
  • D. electionMethod chosen
    Indicates the process or system used to select a candidate or make a decision in an election.
  • E. electoralSystemConcerned
    Indicates that something is related to, affected by, or focused on a particular electoral system.
  • 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_69bd4643f16081908d7f29e08096115a completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd927c946c8190aef40679199fede3 completed March 20, 2026, 6:31 p.m.
PD Predicate disambiguation batch_69bd91a0d96c8190bd1299edbf764bbb completed March 20, 2026, 6:27 p.m.
Created at: March 20, 2026, 2:08 p.m.