Triple

T19449576
Position Surface form Disambiguated ID Type / Status
Subject King Seonjo of Joseon E486577 entity
Predicate capitalDuringReign P9119 FINISHED
Object Han-seong 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: Han-seong | Statement: [King Seonjo of Joseon, capitalDuringReign, Han-seong]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Han-seong
Context triple: [King Seonjo of Joseon, capitalDuringReign, Han-seong]
  • A. Han-seong chosen
    Han-seong was the historical name for Korea’s capital city, now known as Seoul, which served as the political and cultural center of the Joseon dynasty.
  • B. Seonghwan
    Seonghwan is a locality in South Korea historically noted as the site of the Battle of Seonghwan during the First Sino-Japanese War.
  • C. Seonghwa
    Seonghwa was the era name used during the reign of King Seongjong of the Joseon dynasty in Korea, marking a specific period of his rule.
  • D. Yong-taek
    Yong-taek is a Korean masculine given name commonly used in South Korea.
  • E. Chung-ho
    Chung-ho is the former romanized name of Zhonghe District, a populous urban district in New Taipei City, Taiwan.
  • 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_69d8e8d7ad488190a3373045029b0f3b completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e6338caeb48190aeb1d511996984e3 completed April 20, 2026, 2:09 p.m.
Created at: April 10, 2026, 1:38 p.m.