Triple

T18847892
Position Surface form Disambiguated ID Type / Status
Subject Baixa Pombalina E460964 entity
Predicate contains P35 FINISHED
Object Rua da Prata NE NERFINISHED

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: Rua da Prata | Statement: [Baixa Pombalina, contains, Rua da Prata]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rua da Prata
Context triple: [Baixa Pombalina, contains, Rua da Prata]
  • A. Rua da Prata chosen
    Rua da Prata is a historic commercial street in Lisbon’s Baixa district, known for its traditional shops and Pombaline architecture.
  • B. Rua de São Sebastião
    Rua de São Sebastião is a street in Coimbra, Portugal, situated in the historic area near the São Sebastião Aqueduct.
  • C. Rua de São Bento
    Rua de São Bento is a notable street in Lisbon, Portugal, known for housing the Portuguese Parliament building and connecting key areas of the city’s historic center.
  • D. Rua do Ouro
    Rua do Ouro is a historic commercial street in central Lisbon, Portugal, known for its traditional shops and location in the Baixa district.
  • E. Rodovia Dom Pedro I
    Rodovia Dom Pedro I is a major Brazilian highway in the state of São Paulo that connects important interior cities and serves as a key corridor for regional commerce and travel.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8dcfa11e4819090ab1ef5bdcd2b2e completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5b8f079b881908759135c5e2619ee completed April 20, 2026, 5:26 a.m.
Created at: April 10, 2026, 11:56 a.m.