Triple

T4534972
Position Surface form Disambiguated ID Type / Status
Subject Topo de Coroa E107385 entity
Predicate locatedOn P40 FINISHED
Object Santo Antão E107385 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: Santo Antão | Statement: [Topo de Coroa, locatedOn, Santo Antão]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Santo Antão
Context triple: [Topo de Coroa, locatedOn, Santo Antão]
  • A. Santo Antão chosen
    Santo Antão is the westernmost and one of the largest islands of Cape Verde, renowned for its dramatic volcanic mountains, deep valleys, and lush hiking landscapes.
  • B. Tarrafal de São Nicolau
    Tarrafal de São Nicolau is a coastal town and important population center on the island of São Nicolau in Cape Verde.
  • C. Campomoro
    Campomoro is a small coastal village and seaside resort on the southwest coast of Corsica, known for its scenic bay and historic Genoese tower.
  • D. São Jorge Island
    São Jorge Island is a long, narrow volcanic island in the central group of Portugal’s Azores archipelago, known for its dramatic cliffs, fajãs (coastal plains), and traditional cheese production.
  • E. Ilhéu das Rolas
    Ilhéu das Rolas is a small tropical island off the southern tip of São Tomé, notable for being crossed by the equator and for its beaches and ecotourism.
  • 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_69bd43f922788190b7edfa294e39b178 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd57a2301c8190aa59280a16750156 completed March 20, 2026, 2:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69bdacf016d0819080665256c84d37a3 completed March 20, 2026, 8:24 p.m.
Created at: March 20, 2026, 1:04 p.m.