Triple

T7769839
Position Surface form Disambiguated ID Type / Status
Subject Brava (Cape Verde) E179040 entity
Predicate hasPort P35 FINISHED
Object Furna
Furna is a coastal settlement on the Cape Verdean island of Brava that serves as its main maritime gateway and ferry port.
E687579 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: Furna | Statement: [Brava (Cape Verde), hasPort, Furna]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Furna
Context triple: [Brava (Cape Verde), hasPort, Furna]
  • A. Achada Furna
    Achada Furna is a small village located on the island of Fogo in Cape Verde, known for its proximity to the island’s active volcano and its agricultural surroundings.
  • B. Furnas Valley
    Furnas Valley is a geothermal valley on São Miguel Island in the Azores, known for its hot springs, volcanic calderas, and lush, scenic landscapes.
  • C. Aitna
    Aitna is a primordial Greek mountain deity associated with Mount Etna and the volcanic forces of the earth.
  • D. Baturité
    Baturité is a municipality in the state of Ceará in northeastern Brazil, known for its mountainous terrain and relatively mild climate.
  • E. Loutra Nisyrou
    Loutra Nisyrou is a coastal village and spa area on the Greek island of Nisyros, known for its therapeutic thermal springs and seaside baths.
  • 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: Furna
Triple: [Brava (Cape Verde), hasPort, Furna]
Generated description
Furna is a coastal settlement on the Cape Verdean island of Brava that serves as its main maritime gateway and ferry port.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Furna
Target entity description: Furna is a coastal settlement on the Cape Verdean island of Brava that serves as its main maritime gateway and ferry port.
  • A. Achada Furna
    Achada Furna is a small village located on the island of Fogo in Cape Verde, known for its proximity to the island’s active volcano and its agricultural surroundings.
  • B. Furnas Valley
    Furnas Valley is a geothermal valley on São Miguel Island in the Azores, known for its hot springs, volcanic calderas, and lush, scenic landscapes.
  • C. Aitna
    Aitna is a primordial Greek mountain deity associated with Mount Etna and the volcanic forces of the earth.
  • D. Baturité
    Baturité is a municipality in the state of Ceará in northeastern Brazil, known for its mountainous terrain and relatively mild climate.
  • E. Loutra Nisyrou
    Loutra Nisyrou is a coastal village and spa area on the Greek island of Nisyros, known for its therapeutic thermal springs and seaside baths.
  • 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_69c69f30602c819082ab52cd4af5c592 completed March 27, 2026, 3:16 p.m.
NER Named-entity recognition batch_69c70438ca2481909114b0c434717109 completed March 27, 2026, 10:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8c7e7818c8190920ea2bde6343968 completed March 29, 2026, 6:34 a.m.
NEDg Description generation batch_69c8c8698a388190a47d6636fe5d2bb4 completed March 29, 2026, 6:36 a.m.
NED2 Entity disambiguation (via description) batch_69c8c8f3873481908ef6efb2e39272db completed March 29, 2026, 6:38 a.m.
Created at: March 27, 2026, 4:11 p.m.