Triple

T11012479
Position Surface form Disambiguated ID Type / Status
Subject Kam language E260275 entity
Predicate name P16 FINISHED
Object Dong E287513 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: Dong | Statement: [Kam language, name, Dong]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dong
Context triple: [Kam language, name, Dong]
  • A. Dong chosen
    The Dong are an ethnic minority group in China, known for their distinctive wooden architecture, polyphonic folk singing, and concentration in the mountainous regions of southern China, including Guizhou Province.
  • B. Dongfang
    Dongfang is a county-level coastal city in western Hainan Province, China, known for its tropical climate and maritime economy.
  • C. Dongbi
    Dongbi is the courtesy name of Li Shizhen, the renowned Ming dynasty physician and naturalist best known for compiling the monumental herbal pharmacopeia "Compendium of Materia Medica."
  • D. Dongyu
    Dongyu is the given name of Qu Dongyu, a Chinese agronomist and politician who has served as Director-General of the Food and Agriculture Organization of the United Nations.
  • E. Dongsheng
    Dongsheng is a Chinese given name commonly used for males.
  • 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_69d6aa9687448190b28d353b1b6a610e completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d7978a57a881909b4ceae0ebe21b78 completed April 9, 2026, 12:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69e374ac78348190a8c0a5a7a736b24b completed April 18, 2026, 12:10 p.m.
Created at: April 8, 2026, 9:25 p.m.