Triple

T11796531
Position Surface form Disambiguated ID Type / Status
Subject West Africans E280517 entity
Predicate speaksLanguage P741 FINISHED
Object Akan language E151062 NE 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: Akan language | Statement: [West Africans, speaksLanguage, Akan language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Akan language
Context triple: [West Africans, speaksLanguage, Akan language]
  • A. Akan language chosen
    Akan is a Central Tano language of the Niger-Congo family spoken primarily in Ghana, where it serves as a major lingua franca and vehicle of Akan culture.
  • B. Akebu language
    The Akebu language is a Niger-Congo language spoken primarily by the Akebu people in parts of Togo and Ghana.
  • C. Akoko languages
    The Akoko languages are a small group of closely related Niger-Congo languages spoken primarily in the Akoko region of southwestern Nigeria.
  • D. Aka-Kede language
    The Aka-Kede language is an extinct Ongan language once spoken by the indigenous Andamanese Aka-Kede people of North Andaman Island in India.
  • E. Sango language
    Sango is a Central African lingua franca and national language of the Central African Republic, originating as a Ngbandi-based trade language and now used widely in government, education, and daily communication.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69d6ab258b808190b1735835c841e3a4 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d8a5a1cda0819092d66a82fd882786 completed April 10, 2026, 7:24 a.m.
NED1 Entity disambiguation (via context triple) batch_69f131110aa081909aa0b0d532e473a5 completed April 28, 2026, 10:13 p.m.
Created at: April 8, 2026, 9:42 p.m.