Triple

T70096
Position Surface form Disambiguated ID Type / Status
Subject Africa E1402 entity
Predicate hasMajorLanguageFamily P1047 FINISHED
Object Afroasiatic languages E4254 NE FINISHED

How this triple was built (3 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: Afroasiatic languages | Statement: [Africa, hasMajorLanguageFamily, Afroasiatic languages]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Afroasiatic languages
Context triple: [Africa, hasMajorLanguageFamily, Afroasiatic languages]
  • A. Central Semitic languages
    Central Semitic languages are a major branch of the Semitic language family that includes Arabic and several closely related languages of the Middle East.
  • B. Berber languages chosen
    The Berber languages are a group of closely related Afroasiatic languages traditionally spoken by the Indigenous Amazigh peoples of North Africa, particularly in countries such as Morocco, Algeria, Libya, and Tunisia.
  • C. Anatolian languages
    Anatolian languages are an extinct branch of the Indo-European language family once spoken in ancient Anatolia, including languages such as Hittite and Luwian.
  • D. Indo-European language family
    The Indo-European language family is a major global language group that includes many of the world’s most widely spoken languages across Europe and large parts of Asia.
  • E. West African languages
    West African languages are a diverse group of Niger-Congo and other language families spoken across West Africa that have significantly influenced the vocabulary, grammar, and phonology of many Atlantic and Caribbean creoles.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasMajorLanguageFamily
Context triple: [Africa, hasMajorLanguageFamily, Afroasiatic languages]
  • A. languageFamily chosen
    Indicates that two or more languages belong to the same genealogical language family or linguistic lineage.
  • B. hasSignificantLanguage
    Indicates that an entity possesses a language that plays an important or primary role in its communication, identity, or functioning.
  • C. hasLanguageGroup
    Indicates that an entity belongs to, is associated with, or is categorized under a particular language group.
  • D. hasMajorDialectGroup
    Indicates that an entity (typically a language) is associated with a primary or major dialect group to which it belongs.
  • E. hasProtoLanguage
    Indicates that a language or language family originates from, or is derived from, a specified proto-language.
  • F. None of above.

Provenance (4 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_69a24c06b3bc8190aa4ac89026115efc completed Feb. 28, 2026, 1:59 a.m.
NER Named-entity recognition batch_69a24fd16c248190a6ee4cd96c388772 completed Feb. 28, 2026, 2:15 a.m.
NED1 Entity disambiguation (via context triple) batch_69a25abaa7dc8190b65fa9d213a40790 completed Feb. 28, 2026, 3:02 a.m.
PD Predicate disambiguation batch_69a24eaa0df88190add55579b2b9fd02 completed Feb. 28, 2026, 2:10 a.m.
Created at: Feb. 28, 2026, 2:03 a.m.