Triple

T6557966
Position Surface form Disambiguated ID Type / Status
Subject Mamfe languages E152498 entity
Predicate hasLanguage P15 FINISHED
Object Kendem language
The Kendem language is a Bantoid language of the Mamfe group spoken by a small community in southwestern Cameroon.
 E602485 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: Kendem language | Statement: [Mamfe languages, hasLanguage, Kendem language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kendem language
Context triple: [Mamfe languages, hasLanguage, Kendem language]
  • A. Nendö language
    The Nendö language is an Oceanic language spoken on Nendö Island in the Solomon Islands’ Temotu Province.
  • B. Damana language
    The Damana language is an indigenous Chibchan tongue spoken by the Wiwa people of the Sierra Nevada de Santa Marta region in northern Colombia.
  • C. Kamviri language
    The Kamviri language is a Nuristani language spoken primarily by the Kam people in parts of eastern Afghanistan and neighboring regions of Pakistan.
  • D. Kumbewaha language
    The Kumbewaha language is an Austronesian language spoken in Sulawesi, Indonesia, belonging to the Wotu–Wolio subgroup.
  • E. Korandje language
    The Korandje language is a highly endangered Afro-Asiatic language spoken in the oasis town of Tabelbala in southwestern Algeria, notable for its heavy influence from Berber and Arabic.
  • 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: Kendem language
Triple: [Mamfe languages, hasLanguage, Kendem language]
Generated description
The Kendem language is a Bantoid language of the Mamfe group spoken by a small community in southwestern Cameroon.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kendem language
Target entity description: The Kendem language is a Bantoid language of the Mamfe group spoken by a small community in southwestern Cameroon.
  • A. Nendö language
    The Nendö language is an Oceanic language spoken on Nendö Island in the Solomon Islands’ Temotu Province.
  • B. Damana language
    The Damana language is an indigenous Chibchan tongue spoken by the Wiwa people of the Sierra Nevada de Santa Marta region in northern Colombia.
  • C. Kamviri language
    The Kamviri language is a Nuristani language spoken primarily by the Kam people in parts of eastern Afghanistan and neighboring regions of Pakistan.
  • D. Kumbewaha language
    The Kumbewaha language is an Austronesian language spoken in Sulawesi, Indonesia, belonging to the Wotu–Wolio subgroup.
  • E. Korandje language
    The Korandje language is a highly endangered Afro-Asiatic language spoken in the oasis town of Tabelbala in southwestern Algeria, notable for its heavy influence from Berber and Arabic.
  • 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_69c688058d6881908c19b309cc55dbfa completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6ae1eb0888190a67b850ac2bca79c completed March 27, 2026, 4:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6cb8bae88819089cff70fa1101a39 completed March 27, 2026, 6:25 p.m.
NEDg Description generation batch_69c6cd417d288190868e9709deb4b28a completed March 27, 2026, 6:32 p.m.
NED2 Entity disambiguation (via description) batch_69c6ce6be1f88190bc8b90bf90c6dc55 completed March 27, 2026, 6:37 p.m.
Created at: March 27, 2026, 1:52 p.m.