Triple

T16092816
Position Surface form Disambiguated ID Type / Status
Subject Tarrafal de São Nicolau E390399 entity
Predicate containsSettlement P847 FINISHED
Object Ribeira Funda
Ribeira Funda is a small settlement located in the municipality of Tarrafal de São Nicolau on the island of São Nicolau in Cape Verde.
E1198458 NE FINISHED

How this triple was built (4 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: Ribeira Funda | Statement: [Tarrafal de São Nicolau, containsSettlement, Ribeira Funda]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ribeira Funda
Context triple: [Tarrafal de São Nicolau, containsSettlement, Ribeira Funda]
  • A. Ribeirinha
    Ribeirinha is a civil parish located within the municipality of Angra do Heroísmo on Terceira Island in the Azores, Portugal.
  • B. Ribeirinha
    Ribeirinha is a civil parish located on Faial Island in the Azores archipelago of Portugal.
  • C. Ribeirão das Lajes
    Ribeirão das Lajes is a river in the state of Rio de Janeiro, Brazil, known as an important watercourse within the Guandu River basin.
  • D. Carrasqueira
    Carrasqueira is a steep, exposed rock-scramble section on the Pedra da Gávea hiking route in Rio de Janeiro, popular with adventurous climbers and hikers.
  • E. Ribeira Valley
    Ribeira Valley is a region in the state of São Paulo, Brazil, known for its preserved Atlantic Forest, traditional communities, and rich biodiversity.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Ribeira Funda
Triple: [Tarrafal de São Nicolau, containsSettlement, Ribeira Funda]
Generated description
Ribeira Funda is a small settlement located in the municipality of Tarrafal de São Nicolau on the island of São Nicolau in Cape Verde.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ribeira Funda
Target entity description: Ribeira Funda is a small settlement located in the municipality of Tarrafal de São Nicolau on the island of São Nicolau in Cape Verde.
  • A. Ribeirinha
    Ribeirinha is a civil parish located within the municipality of Angra do Heroísmo on Terceira Island in the Azores, Portugal.
  • B. Ribeirinha
    Ribeirinha is a civil parish located on Faial Island in the Azores archipelago of Portugal.
  • C. Ribeirão das Lajes
    Ribeirão das Lajes is a river in the state of Rio de Janeiro, Brazil, known as an important watercourse within the Guandu River basin.
  • D. Carrasqueira
    Carrasqueira is a steep, exposed rock-scramble section on the Pedra da Gávea hiking route in Rio de Janeiro, popular with adventurous climbers and hikers.
  • E. Ribeira Valley
    Ribeira Valley is a region in the state of São Paulo, Brazil, known for its preserved Atlantic Forest, traditional communities, and rich biodiversity.
  • F. None of above. chosen

Provenance (5 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_69d87f198bc48190a8b7e53ca15b7ead completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e1858ed09881909bde122971d95753 completed April 17, 2026, 12:57 a.m.
NED1 Entity disambiguation (via context triple) batch_69fffeed4e008190b1e8d924b9dc9d37 completed May 10, 2026, 3:43 a.m.
NEDg Description generation batch_69ffff8ddb04819091d2261acf823d3c completed May 10, 2026, 3:46 a.m.
NED2 Entity disambiguation (via description) batch_69ffffdb48788190879e733d46393529 completed May 10, 2026, 3:47 a.m.
Created at: April 10, 2026, 4:59 a.m.