Triple

T21996862
Position Surface form Disambiguated ID Type / Status
Subject INTOSAI E543228 entity
Predicate foundedInCity P263 FINISHED
Object Havana NE NERFINISHED

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: Havana | Statement: [INTOSAI, foundedInCity, Havana]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Havana
Context triple: [INTOSAI, foundedInCity, Havana]
  • A. Havana
    "Havana" is a Latin-influenced pop song by Cuban-American singer Camila Cabello that became an international hit and one of her signature tracks.
  • B. Havana chosen
    Havana is the capital and largest city of Cuba, known for its historic architecture, vibrant culture, and central role in the nation’s political and economic life.
  • C. Havana
    Havana is the vibrant capital city of Cuba, renowned for its historic architecture, rich Afro-Cuban culture, and lively music and nightlife.
  • D. Havana
    Havana is the capital and largest city of Cuba, renowned for its historic architecture, vibrant culture, and significant political and economic role in the country.
  • E. Habana
    Habana was the original name of the Confederate ironclad warship later known as CSS Sumter, active during the American Civil War.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e11e2c814c8190837d072789000486 completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f12765fb0c81908f7b7acda065ee2f completed April 28, 2026, 9:32 p.m.
Created at: April 16, 2026, 8:19 p.m.