Triple

T22851503
Position Surface form Disambiguated ID Type / Status
Subject Yi Hwang E566366 entity
Predicate penName P3799 FINISHED
Object Toegye 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: Toegye | Statement: [Yi Hwang, penName, Toegye]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Toegye
Context triple: [Yi Hwang, penName, Toegye]
  • A. Yi Hwang chosen
    Yi Hwang was a prominent 16th-century Korean Confucian scholar and philosopher whose writings and teachings profoundly shaped the development of Neo-Confucian thought in Korea.
  • B. Yi I
    Yi I was a prominent 16th-century Korean scholar-official and philosopher of the Joseon dynasty, renowned for his influential contributions to Neo-Confucian thought and statecraft.
  • C. Jeong Yak-yong
    Jeong Yak-yong was a prominent late Joseon Dynasty Korean scholar, philosopher, and reformer associated with the Silhak (Practical Learning) movement.
  • D. Choe Hang
    Choe Hang was a Korean military leader and statesman who played a key command role during the Mongol invasions of the Korean Peninsula.
  • E. Choe Hang
    Choe Hang was a Joseon Dynasty scholar-official who served in the royal research and advisory institution Jiphyeonjeon, contributing to state scholarship and governance.
  • 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_69e2458750b481908a8e4cf4609cc6cf completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17eb8b3588190b2bc8e7021f9ef10 completed April 29, 2026, 3:44 a.m.
Created at: April 17, 2026, 3:36 p.m.