Triple

T10198650
Position Surface form Disambiguated ID Type / Status
Subject Hmong-Mien E238827 entity
Predicate includesLanguage P2177 FINISHED
Object Kim Mun
Kim Mun is a Hmong-Mien language spoken by the Kim Mun (a subgroup of the Yao/Mien) people in parts of southern China and Southeast Asia.
E848450 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: Kim Mun | Statement: [Hmong-Mien, includesLanguage, Kim Mun]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kim Mun
Context triple: [Hmong-Mien, includesLanguage, Kim Mun]
  • A. Kim Jung-soo
    Kim Jung-soo is a South Korean architect best known for designing the National Assembly Building in Seoul.
  • B. Jang Kum-song
    Jang Kum-song was the daughter of senior North Korean official Kim Kyong-hui and thus a member of North Korea’s ruling Kim family.
  • C. Kim Cheol-ho
    Kim Cheol-ho was a South Korean industrialist and entrepreneur best known as the founder of the automotive company Kia Motors.
  • D. Kim Yong-rae
    Kim Yong-rae is a South Korean politician who served as the mayor of Seoul during the period when the city hosted the 1988 Summer Olympics.
  • E. Paik Nam-june
    Paik Nam-june was a pioneering Korean American artist widely regarded as the founder of video art and a key figure in the development of media and technology-based art.
  • 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: Kim Mun
Triple: [Hmong-Mien, includesLanguage, Kim Mun]
Generated description
Kim Mun is a Hmong-Mien language spoken by the Kim Mun (a subgroup of the Yao/Mien) people in parts of southern China and Southeast Asia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kim Mun
Target entity description: Kim Mun is a Hmong-Mien language spoken by the Kim Mun (a subgroup of the Yao/Mien) people in parts of southern China and Southeast Asia.
  • A. Kim Jung-soo
    Kim Jung-soo is a South Korean architect best known for designing the National Assembly Building in Seoul.
  • B. Jang Kum-song
    Jang Kum-song was the daughter of senior North Korean official Kim Kyong-hui and thus a member of North Korea’s ruling Kim family.
  • C. Kim Cheol-ho
    Kim Cheol-ho was a South Korean industrialist and entrepreneur best known as the founder of the automotive company Kia Motors.
  • D. Kim Yong-rae
    Kim Yong-rae is a South Korean politician who served as the mayor of Seoul during the period when the city hosted the 1988 Summer Olympics.
  • E. Paik Nam-june
    Paik Nam-june was a pioneering Korean American artist widely regarded as the founder of video art and a key figure in the development of media and technology-based art.
  • 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_69d35512ab2c8190b2802c7bb22e7323 completed April 6, 2026, 6:39 a.m.
NEDg Description generation batch_69d35916791081908dfcd1b217390225 completed April 6, 2026, 6:56 a.m.
NED2 Entity disambiguation (via description) batch_69d3597cdf188190853d7385f22e8b26 completed April 6, 2026, 6:58 a.m.
Created at: March 30, 2026, 9:14 p.m.