Triple

T16325899
Position Surface form Disambiguated ID Type / Status
Subject Sé, São Paulo E396416 entity
Predicate hasPart P35 FINISHED
Object Largo São Francisco E953555 NE 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: Largo São Francisco | Statement: [Sé, São Paulo, hasPart, Largo São Francisco]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Largo São Francisco
Context triple: [Sé, São Paulo, hasPart, Largo São Francisco]
  • A. Largo São Francisco chosen
    Largo São Francisco is a historic square in downtown São Paulo known for its traditional law school and colonial-era architecture.
  • B. La Barra
    La Barra is the natural volcanic reef that shelters Las Canteras Beach in Las Palmas de Gran Canaria, creating its calm, protected waters.
  • C. La Barra
    La Barra is a popular seaside resort town in Uruguay known for its beaches, nightlife, and proximity to Punta del Este.
  • D. Barra de São Francisco
    Barra de São Francisco is a municipality in the northwest of the Brazilian state of Espírito Santo, known for its granite mining and agricultural activities.
  • E. Sangre Grande
    Sangre Grande is a major town in northeastern Trinidad known as a regional commercial and transportation hub.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69d87f255b788190a400eba031dd85d8 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e296b9dcb88190beb0ca2206729175 completed April 17, 2026, 8:23 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00260ca9f08190aa95560fea482dd4 completed May 10, 2026, 6:30 a.m.
Created at: April 10, 2026, 5:06 a.m.