Triple

T2950715
Position Surface form Disambiguated ID Type / Status
Subject UNESCO Atlas of the World’s Languages in Danger E79812 entity
Predicate classifiesLanguagesAs P10465 FINISHED
Object vulnerable 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: vulnerable | Statement: [UNESCO Atlas of the World’s Languages in Danger, classifiesLanguagesAs, vulnerable]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: classifiesLanguagesAs
Context triple: [UNESCO Atlas of the World’s Languages in Danger, classifiesLanguagesAs, vulnerable]
  • A. linguisticClassification chosen
    Indicates the relationship by which an entity is categorized according to its language or linguistic type.
  • B. languageAssociation
    Indicates an association or relationship between entities based on a language they use, represent, or are linked to.
  • C. ISO639Macrolanguage
    Indicates that a language variety is part of a broader ISO 639-defined macrolanguage grouping that encompasses multiple closely related individual languages.
  • D. recognizedAsClassicalLanguageBy
    Indicates that an entity is acknowledged or designated by a specified authority or source as a classical language.
  • E. typicalLanguages
    Indicates the languages that are commonly or characteristically used, spoken, or associated with a given entity.
  • 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_69ad8b1276588190a374a0b12e0f7bdf completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad98fbb7d4819081c241f3ff9165e5 completed March 8, 2026, 3:42 p.m.
PD Predicate disambiguation batch_69ad960a70ac8190816b5ae3e8631031 completed March 8, 2026, 3:30 p.m.
Created at: March 8, 2026, 2:57 p.m.