Triple

T7274010
Position Surface form Disambiguated ID Type / Status
Subject Dioula E162977 entity
Predicate hasMacrolanguageRelation P23734 FINISHED
Object Manding macrolanguage LITERAL 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: Manding macrolanguage | Statement: [Dioula, hasMacrolanguageRelation, Manding macrolanguage]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasMacrolanguageRelation
Context triple: [Dioula, hasMacrolanguageRelation, Manding macrolanguage]
  • A. macrolanguageMemberOf
    Indicates that a language variety is classified as a member of a larger macrolanguage grouping.
  • B. macrolanguageOf chosen
    Indicates that one language functions as a macrolanguage encompassing or grouping together one or more related individual languages.
  • C. hasStandardLanguageRelation
    Indicates that there exists a standardized linguistic relationship between two entities, such as one being the standard or reference language form for the other.
  • D. macrolanguage
    Indicates that a language is classified as a macrolanguage encompassing multiple closely related individual languages or varieties.
  • E. ISO639Macrolanguage
    Indicates that a language variety is part of a broader ISO 639-defined macrolanguage grouping that encompasses multiple closely related individual languages.
  • F. None of above.

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_69c6885c5964819085b209701769877f completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6eb8a0b4881908ff27c5a75bd4a95 completed March 27, 2026, 8:41 p.m.
PD Predicate disambiguation batch_69c6e76a84a081908d4184c55b728e48 completed March 27, 2026, 8:24 p.m.
Created at: March 27, 2026, 2:58 p.m.