Triple

T4976769
Position Surface form Disambiguated ID Type / Status
Subject Kui language E111784 entity
Predicate alternativeName P39 FINISHED
Object Kandh language
The Kandh language, also known as Kui, is a Dravidian language spoken primarily by the Kandha (Khond) tribal communities in the Indian state of Odisha.
 E485561 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: Kandh language | Statement: [Kui language, alternativeName, Kandh language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kandh language
Context triple: [Kui language, alternativeName, Kandh language]
  • A. Kangjia language
    The Kangjia language is a lesser-known Mongolic language spoken by the Kangjia people in parts of northwestern China.
  • B. Kam language
    Kam is a Tai–Kadai language spoken primarily by the Kam (Dong) people of southern China, known for its rich tonal system and distinct northern and southern dialects.
  • C. Kaado language
    The Kaado language is a regional variety within the Songhay language family spoken by communities in parts of West Africa.
  • D. Kaxabu language
    The Kaxabu language is an indigenous Formosan language of Taiwan spoken by the Kaxabu people and considered highly endangered.
  • E. Kistane language
    Kistane language is an Ethiopian Semitic language spoken by the Kistane (Soddo) people in central Ethiopia.
  • 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: Kandh language
Triple: [Kui language, alternativeName, Kandh language]
Generated description
The Kandh language, also known as Kui, is a Dravidian language spoken primarily by the Kandha (Khond) tribal communities in the Indian state of Odisha.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kandh language
Target entity description: The Kandh language, also known as Kui, is a Dravidian language spoken primarily by the Kandha (Khond) tribal communities in the Indian state of Odisha.
  • A. Kangjia language
    The Kangjia language is a lesser-known Mongolic language spoken by the Kangjia people in parts of northwestern China.
  • B. Kam language
    Kam is a Tai–Kadai language spoken primarily by the Kam (Dong) people of southern China, known for its rich tonal system and distinct northern and southern dialects.
  • C. Kaado language
    The Kaado language is a regional variety within the Songhay language family spoken by communities in parts of West Africa.
  • D. Kaxabu language
    The Kaxabu language is an indigenous Formosan language of Taiwan spoken by the Kaxabu people and considered highly endangered.
  • E. Kistane language
    Kistane language is an Ethiopian Semitic language spoken by the Kistane (Soddo) people in central Ethiopia.
  • 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_69bd441adc208190b70a033a0741d01e completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd7231448c8190a5d0a5135a9cfdf1 completed March 20, 2026, 4:13 p.m.
NED1 Entity disambiguation (via context triple) batch_69be8a0634b48190acb4a1834f5647cf completed March 21, 2026, 12:07 p.m.
NEDg Description generation batch_69be8a9c72848190978797a33d0d83c8 completed March 21, 2026, 12:10 p.m.
NED2 Entity disambiguation (via description) batch_69be8b3718288190b2fc319fdad0a7c0 completed March 21, 2026, 12:12 p.m.
Created at: March 20, 2026, 1:33 p.m.