Triple

T14010317
Position Surface form Disambiguated ID Type / Status
Subject Nupoid languages E337060 entity
Predicate hasMember P10 FINISHED
Object Kakanda language
The Kakanda language is a Nupoid language spoken by the Kakanda people of Nigeria, belonging to the larger Niger-Congo language family.
 E1073888 NE FINISHED

How this triple was built (4 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: Kakanda language | Statement: [Nupoid languages, hasMember, Kakanda language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kakanda language
Context triple: [Nupoid languages, hasMember, Kakanda language]
  • A. Daakaka language
    The Daakaka language is an Oceanic language spoken by communities on Ambrym Island in Vanuatu.
  • B. Kambaata language
    The Kambaata language is a Cushitic language of the Afroasiatic family spoken primarily by the Kambaata people in southern Ethiopia.
  • C. Kande language
    The Kande language is a Bantu language variety within the Tswa–Ronga group, spoken by communities in southern Africa.
  • D. Kaxabu language
    The Kaxabu language is an indigenous Formosan language of Taiwan spoken by the Kaxabu people and considered highly endangered.
  • E. Kumbewaha language
    The Kumbewaha language is an Austronesian language spoken in Sulawesi, Indonesia, belonging to the Wotu–Wolio subgroup.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Kakanda language
Triple: [Nupoid languages, hasMember, Kakanda language]
Generated description
The Kakanda language is a Nupoid language spoken by the Kakanda people of Nigeria, belonging to the larger Niger-Congo language family.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kakanda language
Target entity description: The Kakanda language is a Nupoid language spoken by the Kakanda people of Nigeria, belonging to the larger Niger-Congo language family.
  • A. Daakaka language
    The Daakaka language is an Oceanic language spoken by communities on Ambrym Island in Vanuatu.
  • B. Kambaata language
    The Kambaata language is a Cushitic language of the Afroasiatic family spoken primarily by the Kambaata people in southern Ethiopia.
  • C. Kande language
    The Kande language is a Bantu language variety within the Tswa–Ronga group, spoken by communities in southern Africa.
  • D. Kaxabu language
    The Kaxabu language is an indigenous Formosan language of Taiwan spoken by the Kaxabu people and considered highly endangered.
  • E. Kumbewaha language
    The Kumbewaha language is an Austronesian language spoken in Sulawesi, Indonesia, belonging to the Wotu–Wolio subgroup.
  • F. None of above. chosen

Provenance (5 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_69d81c645c5c8190b1fd16a285a1b78a completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2ed5cfd0819085b9c860b119a9de completed April 14, 2026, 12:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69fbaca7bbd88190a377d3b74f3d6224 completed May 6, 2026, 9:03 p.m.
NEDg Description generation batch_69fbae6691b48190a0affc662cbb2d4e completed May 6, 2026, 9:11 p.m.
NED2 Entity disambiguation (via description) batch_69fbaf702c94819095347e2599ae9931 completed May 6, 2026, 9:15 p.m.
Created at: April 9, 2026, 10:19 p.m.