Triple

T4089984
Position Surface form Disambiguated ID Type / Status
Subject Platt Amendment E87682 entity
Predicate appliesTo P1129 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: [Platt Amendment, appliesTo, Cuba]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cuba
Context triple: [Platt Amendment, appliesTo, Cuba]
  • A. Cuba chosen
    Cuba is a Caribbean island nation known for its communist government, historic Havana architecture, classic cars, and influential music and culture.
  • B. Cuba
    Cuba is a municipality in Portugal’s Beja District, known for its rural Alentejo landscape and traditional wine production.
  • C. 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.
  • D. 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.
  • E. Grenada
    Grenada is a small Caribbean island nation known for its spice production, picturesque beaches, and lush mountainous interior.
  • 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_69aed94425148190be337845d56fac22 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aefcab0a1c8190a1b0ca48ebc95b31 completed March 9, 2026, 5 p.m.
NED1 Entity disambiguation (via context triple) batch_69b589d525fc8190be388452c220832e completed March 14, 2026, 4:16 p.m.
Created at: March 9, 2026, 3:39 p.m.