Triple

T22863982
Position Surface form Disambiguated ID Type / Status
Subject Lavra Funicular E567000 entity
Predicate connects P390 FINISHED
Object Rua Câmara Pestana 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 Câmara Pestana | Statement: [Lavra Funicular, connects, Rua Câmara Pestana]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rua Câmara Pestana
Context triple: [Lavra Funicular, connects, Rua Câmara Pestana]
  • A. Rua Câmara Pestana chosen
    Rua Câmara Pestana is a street in Lisbon, Portugal, known as the upper endpoint of the historic Elevador do Lavra funicular.
  • B. Rua da Madalena
    Rua da Madalena is a historic street in Lisbon’s city center, known for its traditional shops and proximity to major downtown landmarks.
  • C. Rua da Rosa
    Rua da Rosa is a historic street located in central Lisbon, Portugal, known for its traditional architecture and urban charm.
  • D. Rua da Barroca
    Rua da Barroca is a historic street located in the old São Nicolau area of central Porto, Portugal.
  • E. Rua do Carmo
    Rua do Carmo is a well-known shopping street in central Lisbon, Portugal, lined with historic buildings, boutiques, and cafés connecting the Chiado and Baixa districts.
  • 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_69e24589083081908d5694c4fdc80086 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17eff1c18819081dc9dfc1816f746 completed April 29, 2026, 3:46 a.m.
Created at: April 17, 2026, 3:38 p.m.