Triple

T9005825
Position Surface form Disambiguated ID Type / Status
Subject Zhangzhou E215140 entity
Predicate hasLanguage P15 FINISHED
Object Hokkien E410805 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: Hokkien | Statement: [Zhangzhou, hasLanguage, Hokkien]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hokkien
Context triple: [Zhangzhou, hasLanguage, Hokkien]
  • A. Hokkien chosen
    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.
  • B. Nanbu
    Nanbu is a town in Shizuoka Prefecture, Japan, known for its rural landscape and location near the border with Yamanashi Prefecture.
  • C. Kahama
    Kahama is a town and district-level administrative center in northwestern Tanzania known for its mining activities and role as a commercial hub in the Shinyanga area.
  • D. Hokkedō
    Hokkedō is one of the oldest surviving halls at the Tōdai-ji temple complex in Nara, Japan, renowned for its historic Buddhist statues and early Nara-period architecture.
  • E. Hànshū
    Hànshū is the standard pinyin title of the "Book of Han," a major Chinese historical text documenting the history of the Western Han dynasty.
  • 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_69ca83a12d648190b1e4fe11e8a31890 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc69bc6e208190b0c01e3761c04799 completed April 1, 2026, 12:41 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfd0e3f0c88190ae688632be25e5c9 completed April 3, 2026, 2:38 p.m.
Created at: March 30, 2026, 7:05 p.m.