Triple

T9484169
Position Surface form Disambiguated ID Type / Status
Subject Hoklo people E228717 entity
Predicate nativeTo P410 FINISHED
Object Hainan E37179 NE FINISHED

How this triple was built (2 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: Hainan | Statement: [Hoklo people, nativeTo, Hainan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hainan
Context triple: [Hoklo people, nativeTo, Hainan]
  • A. Hainan chosen
    Hainan is a tropical island province in southern China known for its beaches, tourism, and status as a major special economic zone.
  • B. Qizhou
    Qizhou is a historic town in Hubei, China, known as the birthplace of the famed Ming dynasty physician and pharmacologist Li Shizhen.
  • C. Wenchang
    Wenchang is a coastal city in northeastern Hainan, China, known as a cultural center and important homeland of many overseas Chinese.
  • D. Xingsha
    Xingsha is a town in Changsha County, Hunan Province, China, known as the modern urban area closest to the famous Mawangdui Han Tombs archaeological site.
  • E. Paiwan
    The Paiwan are one of Taiwan’s major Indigenous groups, known for their hierarchical social structure, rich oral traditions, and distinctive artistic practices such as woodcarving and beadwork.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69ca84730a5081908de282651019bf2f completed March 30, 2026, 2:10 p.m.
NER Named-entity recognition batch_69cd804e278c8190b1f869158075cd52 completed April 1, 2026, 8:30 p.m.
NED1 Entity disambiguation (via context triple) batch_69d152670dcc8190abcaabbd62c97a34 completed April 4, 2026, 6:03 p.m.
Created at: March 30, 2026, 7:55 p.m.