Triple

T20203579
Position Surface form Disambiguated ID Type / Status
Subject Codrington Airport E493287 entity
Predicate cityServed P82 FINISHED
Object Codrington 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: Codrington | Statement: [Codrington Airport, cityServed, Codrington]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Codrington
Context triple: [Codrington Airport, cityServed, Codrington]
  • A. Codrington
    Codrington is an English surname historically associated with notable figures in the British Royal Navy and colonial administration.
  • B. Codrington chosen
    Codrington is the main town and administrative center of the Caribbean island of Barbuda, part of the nation of Antigua and Barbuda.
  • C. Vieux Fort Bay
    Vieux Fort Bay is a coastal inlet in the southern part of Saint Lucia known for its beaches, marine activity, and proximity to the town of Vieux Fort.
  • D. Port Morant
    Port Morant is a coastal town in eastern Jamaica known historically as one of the island’s early ports and plantation centers.
  • E. Salt Cay
    Salt Cay is a small, sparsely populated island in the Turks and Caicos known for its historic salt industry, quiet beaches, and excellent whale-watching opportunities.
  • 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_69da6269614c8190bb40475d9d477358 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e66d8f90108190b72e37c0056de0f8 completed April 20, 2026, 6:16 p.m.
Created at: April 11, 2026, 11:38 p.m.