Triple

T21824915
Position Surface form Disambiguated ID Type / Status
Subject Taa E538823 entity
Predicate hasDialect P4251 FINISHED
Object ǂHuan
ǂHuan is a dialect of the Taa language, a highly complex Khoisan language spoken in parts of southern Africa and noted for its extensive click consonant system.
 E1503872 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: ǂHuan | Statement: [Taa, hasDialect, ǂHuan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: ǂHuan
Context triple: [Taa, hasDialect, ǂHuan]
  • A. Huan
    Huan is a given name most notably associated with the contemporary Chinese artist Zhang Huan, known for his performance and conceptual art.
  • B. Hankutchin
    Hankutchin is an alternative name for the Hän, an Athabaskan-speaking Indigenous people of the Yukon–Alaska border region.
  • C. Harku
    Harku is a small settlement in northern Estonia located within Harku Parish, near the capital city of Tallinn.
  • D. Hau
    Hau is the surname of Danish physicist Lene Vestergaard Hau, known for her pioneering work in slowing and stopping light.
  • E. Hōan
    Hōan was a Japanese era name (nengō) of the early 12th century, used during the reign of Emperor Toba.
  • 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: ǂHuan
Triple: [Taa, hasDialect, ǂHuan]
Generated description
ǂHuan is a dialect of the Taa language, a highly complex Khoisan language spoken in parts of southern Africa and noted for its extensive click consonant system.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: ǂHuan
Target entity description: ǂHuan is a dialect of the Taa language, a highly complex Khoisan language spoken in parts of southern Africa and noted for its extensive click consonant system.
  • A. Huan
    Huan is a given name most notably associated with the contemporary Chinese artist Zhang Huan, known for his performance and conceptual art.
  • B. Hankutchin
    Hankutchin is an alternative name for the Hän, an Athabaskan-speaking Indigenous people of the Yukon–Alaska border region.
  • C. Harku
    Harku is a small settlement in northern Estonia located within Harku Parish, near the capital city of Tallinn.
  • D. Hau
    Hau is the surname of Danish physicist Lene Vestergaard Hau, known for her pioneering work in slowing and stopping light.
  • E. Hōan
    Hōan was a Japanese era name (nengō) of the early 12th century, used during the reign of Emperor Toba.
  • 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_69e0c475038c8190abb9b1a20eb8ff50 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69f091307d408190a92b65c3f39682a8 completed April 28, 2026, 10:51 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0a45e50d548190aaf4ac0bf6fcd028 completed May 17, 2026, 10:49 p.m.
NEDg Description generation batch_6a0a478555f48190a5dec30d212817fa completed May 17, 2026, 10:56 p.m.
NED2 Entity disambiguation (via description) batch_6a0a4816a85c8190b086b93851ddd11c completed May 17, 2026, 10:58 p.m.
Created at: April 16, 2026, 6:54 p.m.