Triple

T22981965
Position Surface form Disambiguated ID Type / Status
Subject CMF E571491 entity
Predicate shortName P43 FINISHED
Object CMF 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: CMF | Statement: [CMF, shortName, CMF]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: CMF
Context triple: [CMF, shortName, CMF]
  • A. CMF
    CMF is the abbreviated name for the Ministerial Conference of La Francophonie, a key governing body within the international Francophone organization.
  • B. CMF
    CMF is the acronym for the Conseil du Marché Financier, Tunisia’s financial market regulatory authority overseeing securities and capital markets.
  • C. CMF
    CMF is the commonly used abbreviation for the Claretian Missionaries, a Roman Catholic religious congregation founded by Saint Anthony Mary Claret dedicated to evangelization, education, and social justice worldwide.
  • D. CMF
    CMF is the IATA airport code for Chambéry Airport, a regional airport in southeastern France serving the Savoie area and nearby Alpine ski destinations.
  • E. CMF
    CMF is the National Rail station code for Cromford railway station in Derbyshire, England.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide. chosen

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_69e245b3c50481908bb3741ec9f40862 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1829645f88190aea1b96ea595ff60 completed April 29, 2026, 4:01 a.m.
Created at: April 17, 2026, 3:49 p.m.