Triple

T14249058
Position Surface form Disambiguated ID Type / Status
Subject State of Maranhão E353208 entity
Predicate capital P234 FINISHED
Object São Luís E354386 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: São Luís | Statement: [State of Maranhão, capital, São Luís]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: São Luís
Context triple: [State of Maranhão, capital, São Luís]
  • A. São Luís chosen
    São Luís is the historic capital of the Brazilian state of Maranhão, known for its well-preserved colonial architecture and rich Afro-Brazilian cultural heritage.
  • B. São Luís
    São Luís is a civil parish in the municipality of Odemira, located in Portugal’s Alentejo region.
  • C. Belém
    Belém is a historic riverside district of Lisbon, Portugal, known for its monuments of the Age of Discoveries, including the Belém Tower and Jerónimos Monastery.
  • D. Belém do Pará
    Belém do Pará is a major port city in northern Brazil, known as the gateway to the Amazon region and an important cultural and economic center.
  • E. Feira de Santana
    Feira de Santana is a major commercial and transportation hub in northeastern Brazil and the second-largest city in the state of Bahia.
  • 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_69d8278c43e08190824146f4632b89a5 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de6295ef9081909cfb0c1283bca21a completed April 14, 2026, 3:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd4c2bbfec81909ade3dd4306d69e3 completed May 8, 2026, 2:36 a.m.
Created at: April 10, 2026, 1:08 a.m.