Triple

T16935006
Position Surface form Disambiguated ID Type / Status
Subject Hokkien E410805 entity
Predicate hasDialects P4251 FINISHED
Object Medan Hokkien E228712 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: Medan Hokkien | Statement: [Hokkien, hasDialects, Medan Hokkien]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Medan Hokkien
Context triple: [Hokkien, hasDialects, Medan Hokkien]
  • A. Medan Hokkien chosen
    Medan Hokkien is a regional variety of the Hokkien Chinese language spoken primarily by Chinese communities in and around Medan, North Sumatra, Indonesia.
  • B. Hokkien
    Hokkien is a Southern Min Chinese language variety widely spoken in Taiwan, Southeast Asia, and parts of southern China, known for its rich tonal system and distinct vocabulary from Mandarin.
  • C. Nanyang
    Nanyang is a major prefecture-level city in southwestern Henan Province, China, known for its long history, cultural heritage, and role as a regional economic and transportation hub.
  • D. Tsingtau
    Tsingtau is the former German colonial name for the Chinese port city now known as Qingdao, located on the Shandong Peninsula.
  • E. Caizhou
    Caizhou was a historic Chinese city best known as the final capital of the Jurchen-led Jin dynasty before its fall to the Mongols.
  • 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_69d886c886688190967be07322597ac9 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3cf2899608190a6bacdce9d4ceb84 completed April 18, 2026, 6:36 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00cfe2d4f48190b965b6c0a3cc0125 completed May 10, 2026, 6:35 p.m.
Created at: April 10, 2026, 5:30 a.m.