Triple

T7824621
Position Surface form Disambiguated ID Type / Status
Subject Former Han E181215 entity
Predicate currency P245 FINISHED
Object Wuzhu coin E457185 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: Wuzhu coin | Statement: [Former Han, currency, Wuzhu coin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Wuzhu coin
Context triple: [Former Han, currency, Wuzhu coin]
  • A. Banliang coin
    The Banliang coin was an early standardized round bronze coin with a square hole that became the model for later Chinese cash coins.
  • B. Wu Zhu cash coins chosen
    Wu Zhu cash coins were small round bronze coins with square holes that served as the standard form of money in China for centuries, including during the Sui dynasty.
  • C. Kaiyuan Tongbao cash coins
    Kaiyuan Tongbao cash coins are early medieval Chinese bronze currency pieces first issued under Emperor Gaozu that became a standard model for later East Asian coinage.
  • D. Pagoda (gold coin)
    The Pagoda was a high-value South Indian gold coin widely used in trade and taxation, especially under the Vijayanagara Empire and later regional powers.
  • E. Yuan
    Yuan is a common Chinese surname with historical roots and notable bearers in business, politics, and the arts.
  • 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_69ca8282ccec819083c48efb72d21cf9 completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cafa0c1f5c8190b16db20daad159a1 completed March 30, 2026, 10:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69cb5a715bbc8190923ef94ccf91c878 completed March 31, 2026, 5:24 a.m.
Created at: March 30, 2026, 4:42 p.m.