Triple

T10198652
Position Surface form Disambiguated ID Type / Status
Subject Hmong-Mien E238827 entity
Predicate includesLanguage P2177 FINISHED
Object Bunu
Bunu is a Hmong-Mien language spoken by the Bunu people, primarily in southern China.
 E846808 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: Bunu | Statement: [Hmong-Mien, includesLanguage, Bunu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Bunu
Context triple: [Hmong-Mien, includesLanguage, Bunu]
  • A. Bunun people
    The Bunun people are an indigenous Austronesian ethnic group of Taiwan, traditionally known as highland farmers and hunters with rich polyphonic vocal music and distinct cultural practices.
  • B. Buna
    Buna is the Nazi concentration and labor camp complex near Auschwitz where Elie Wiesel is imprisoned in his memoir "Night."
  • C. Buna
    Buna is a coastal village in Papua New Guinea that was a key site of intense fighting between Allied and Japanese forces during World War II’s New Guinea campaign.
  • D. Buna
    Buna is a short but significant karst river in Bosnia and Herzegovina, renowned for its powerful spring at Blagaj and its contribution to the Neretva river system.
  • E. BUT
    BUT is the commonly used abbreviation for Brno University of Technology, a major technical university located in Brno, Czech Republic.
  • 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: Bunu
Triple: [Hmong-Mien, includesLanguage, Bunu]
Generated description
Bunu is a Hmong-Mien language spoken by the Bunu people, primarily in southern China.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Bunu
Target entity description: Bunu is a Hmong-Mien language spoken by the Bunu people, primarily in southern China.
  • A. Bunun people
    The Bunun people are an indigenous Austronesian ethnic group of Taiwan, traditionally known as highland farmers and hunters with rich polyphonic vocal music and distinct cultural practices.
  • B. Buna
    Buna is a short but significant karst river in Bosnia and Herzegovina, renowned for its powerful spring at Blagaj and its contribution to the Neretva river system.
  • C. Buna
    Buna is the Nazi concentration and labor camp complex near Auschwitz where Elie Wiesel is imprisoned in his memoir "Night."
  • D. Buna
    Buna is a coastal village in Papua New Guinea that was a key site of intense fighting between Allied and Japanese forces during World War II’s New Guinea campaign.
  • E. BUT
    BUT is the commonly used abbreviation for Brno University of Technology, a major technical university located in Brno, Czech Republic.
  • 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_69ca84e1ea088190b38162e43d4cfa8f completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cdee3dfa108190b2888385ef96de23 completed April 2, 2026, 4:19 a.m.
NED1 Entity disambiguation (via context triple) batch_69d317eca3f88190a47009be6f96977e completed April 6, 2026, 2:18 a.m.
NEDg Description generation batch_69d319cb6e8c8190926bacedd18f5ded completed April 6, 2026, 2:26 a.m.
NED2 Entity disambiguation (via description) batch_69d31a5417f48190ac4449b44b555320 completed April 6, 2026, 2:28 a.m.
Created at: March 30, 2026, 9:14 p.m.