Triple

T21868652
Position Surface form Disambiguated ID Type / Status
Subject Yi Do E539947 entity
Predicate birthName P65 FINISHED
Object Yi Do 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: Yi Do | Statement: [Yi Do, birthName, Yi Do]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yi Do
Context triple: [Yi Do, birthName, Yi Do]
  • A. Yi Do chosen
    Yi Do, better known as Sejong the Great, was the fourth king of Korea’s Joseon dynasty and is renowned for creating the Korean alphabet Hangul and promoting major cultural and scientific advancements.
  • B. Kim Yu-sin
    Kim Yu-sin was a renowned 7th-century Korean general and statesman who played a decisive role in unifying the Korean Peninsula under the Silla kingdom.
  • C. Kim Ji-yong
    Kim Ji-yong is a South Korean cinematographer known for his work on the film "Silenced."
  • D. Kong Ji
    Kong Ji was a Chinese philosopher of the late Spring and Autumn period, the grandson of Confucius, traditionally regarded as the author of the Confucian classic "Doctrine of the Mean."
  • E. Ong Ye Kung
    Ong Ye Kung is a Singaporean politician who has served as Minister for Health and previously held key portfolios in education and transport.
  • 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_69e0c478f59081909d54302b57fc1ce3 completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f0f33305d081908cd070134420607a completed April 28, 2026, 5:49 p.m.
Created at: April 16, 2026, 6:57 p.m.