Triple

T18838981
Position Surface form Disambiguated ID Type / Status
Subject Cesária Évora Airport E460740 entity
Predicate timezone P109 FINISHED
Object CVT 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: CVT | Statement: [Cesária Évora Airport, timezone, CVT]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: CVT
Context triple: [Cesária Évora Airport, timezone, CVT]
  • A. CVT
    CVT is the three-letter IATA airport code assigned to Coventry Airport in the United Kingdom.
  • B. CVT chosen
    CVT is the standard time zone used in Cape Verde, operating at a fixed offset from Coordinated Universal Time.
  • C. Xtronic CVT
    Xtronic CVT is Nissan’s continuously variable automatic transmission system designed to deliver smoother acceleration and improved fuel efficiency in its vehicles.
  • D. 5MT
    5MT is the British Railways power classification denoting a mixed-traffic steam locomotive of medium power, famously applied to the LMS Black Five class.
  • E. CV8
    CV8 is a high-performance, limited-edition variant of the Holden Monaro sports coupe, distinguished by upgraded power, handling, and unique styling features.
  • 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_69d8dcfa11e4819090ab1ef5bdcd2b2e completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5a9a0a9a48190b19b131f06b6f72f completed April 20, 2026, 4:20 a.m.
Created at: April 10, 2026, 11:56 a.m.