Triple

T20646196
Position Surface form Disambiguated ID Type / Status
Subject Mun E507361 entity
Predicate replacedBy P101 FINISHED
Object Korean won NE NERFINISHED

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: Korean won | Statement: [Mun, replacedBy, Korean won]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Korean won
Context triple: [Mun, replacedBy, Korean won]
  • A. South Korean won
    The South Korean won is the official currency of South Korea, known for its significant devaluation and subsequent reforms during the late-1990s Asian financial crisis.
  • B. Korean yen (early period) chosen
    The Korean yen (early period) was the Japanese-era currency that continued in circulation in southern Korea under the United States Army Military Government immediately after World War II, before being replaced by the South Korean won.
  • C. Yen
    Yen is a nimble and acrobatic member of Danny Ocean’s heist crew in the Ocean’s film series, renowned for his contortionist skills.
  • D. Yen
    Yen is the Wade–Giles romanization of the Chinese surname commonly spelled "Yan" in pinyin.
  • E. Yen
    Yen is a skilled and formidable assassin featured in the television series "The Continental: From the World of John Wick."
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b4be702c8190a3d2410a881d310a completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6af1eee9c81908fd3b4fe8c4529c8 completed April 20, 2026, 10:56 p.m.
Created at: April 16, 2026, 11:43 a.m.