Triple

T16325939
Position Surface form Disambiguated ID Type / Status
Subject Helene Bradley E396417 entity
Predicate appearsInFictionalSetting P98600 FINISHED
Object Cuba E10524 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: Cuba | Statement: [Helene Bradley, appearsInFictionalSetting, Cuba]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cuba
Context triple: [Helene Bradley, appearsInFictionalSetting, Cuba]
  • A. Cuba
    Cuba is a municipality in Portugal’s Beja District, known for its rural Alentejo landscape and traditional wine production.
  • B. Cuba chosen
    Cuba is a Caribbean island nation known for its communist government, historic Havana architecture, classic cars, and influential music and culture.
  • C. Cubão
    Cubão is a locality in the state of São Paulo, Brazil, situated near the industrial city of São Bernardo do Campo.
  • D. Dominican Republic
    The Dominican Republic is a Caribbean nation on the island of Hispaniola known for its beaches, mountainous interior, and vibrant blend of Spanish, African, and Taíno cultural influences.
  • E. Haiti
    Haiti is a Caribbean nation on the island of Hispaniola known for its rich Afro-Caribbean culture, history as the first independent Black republic, and frequent vulnerability to natural disasters.
  • 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_69d87f255b788190a400eba031dd85d8 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e296b9dcb88190beb0ca2206729175 completed April 17, 2026, 8:23 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00260ca9f08190aa95560fea482dd4 completed May 10, 2026, 6:30 a.m.
Created at: April 10, 2026, 5:06 a.m.