Triple

T23022999
Position Surface form Disambiguated ID Type / Status
Subject Penghu County E573217 entity
Predicate commonLanguages P237 FINISHED
Object Penghu dialect of Hokkien NE NERFINISHED

How this triple was built (3 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: Penghu dialect of Hokkien | Statement: [Penghu County, commonLanguages, Penghu dialect of Hokkien]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Penghu dialect of Hokkien
Context triple: [Penghu County, commonLanguages, Penghu dialect of Hokkien]
  • A. Kinmen dialect of Hokkien
    The Kinmen dialect of Hokkien is a regional variety of Southern Min Chinese spoken on Kinmen Island, closely related to Taiwanese Hokkien but preserving several older phonological and lexical features.
  • B. Taiwanese Hokkien
    Taiwanese Hokkien is a Southern Min Chinese language variety widely spoken in Taiwan, where it serves as a major vernacular and cultural language alongside Mandarin.
  • C. Hokkien (Southern Min)
    Hokkien (Southern Min) is a major Sinitic language variety spoken primarily in southern Fujian, Taiwan, and among overseas Chinese communities in Southeast Asia.
  • D. Matsu dialect (Eastern Min)
    The Matsu dialect (Eastern Min) is a variety of the Eastern Min Chinese language spoken primarily in the Matsu Islands off the coast of Fujian, known for its close relation to the Fuzhou dialect and distinctive phonology.
  • E. Sze Yup dialect
    The Sze Yup dialect is a major variety of Cantonese historically spoken in the Siyi (Four Counties) region of Guangdong, China, and by many overseas Chinese communities originating from that area.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Penghu dialect of Hokkien
Target entity description: The Penghu dialect of Hokkien is a regional variety of Southern Min spoken in Taiwan’s Penghu archipelago, characterized by distinctive phonological and lexical features compared with other Taiwanese Hokkien dialects.
  • A. Kinmen dialect of Hokkien
    The Kinmen dialect of Hokkien is a regional variety of Southern Min Chinese spoken on Kinmen Island, closely related to Taiwanese Hokkien but preserving several older phonological and lexical features.
  • B. Taiwanese Hokkien
    Taiwanese Hokkien is a Southern Min Chinese language variety widely spoken in Taiwan, where it serves as a major vernacular and cultural language alongside Mandarin.
  • C. Hokkien (Southern Min)
    Hokkien (Southern Min) is a major Sinitic language variety spoken primarily in southern Fujian, Taiwan, and among overseas Chinese communities in Southeast Asia.
  • D. Matsu dialect (Eastern Min)
    The Matsu dialect (Eastern Min) is a variety of the Eastern Min Chinese language spoken primarily in the Matsu Islands off the coast of Fujian, known for its close relation to the Fuzhou dialect and distinctive phonology.
  • E. Sze Yup dialect
    The Sze Yup dialect is a major variety of Cantonese historically spoken in the Siyi (Four Counties) region of Guangdong, China, and by many overseas Chinese communities originating from that area.
  • F. None of above. chosen

Provenance (2 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_69e245b821008190b0e09cb02092aae1 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f183ea23088190b2f42d9bf01514ac completed April 29, 2026, 4:07 a.m.
Created at: April 17, 2026, 3:52 p.m.