Triple

T12057534
Position Surface form Disambiguated ID Type / Status
Subject 孫基禎 E287080 entity
Predicate name P16 FINISHED
Object 孫基禎 E287080 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: 孫基禎 | Statement: [孫基禎, name, 孫基禎]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: 孫基禎
Context triple: [孫基禎, name, 孫基禎]
  • A. 孫基禎 chosen
    孫基禎 was a Korean marathon runner who won the gold medal at the 1936 Berlin Olympics while competing under the Japanese name Son Kitei during Japan’s colonial rule over Korea.
  • B. Lee Yong-ik
    Lee Yong-ik was a prominent Korean educator and nationalist who played a key role in modernizing education in Korea and helped establish Korea University as a leading institution of higher learning.
  • C. 윤치호
    윤치호는 대한제국과 일제강점기 초기에 활동한 개화파 정치가이자 교육자·외교관으로, 한국 근대사와 민족운동, 그리고 초기 애국가 가사와 관련된 인물이다.
  • D. Cho Yo-han
    Cho Yo-han is the Korean birth name of John Cho, a Korean American actor best known for his roles in the "Harold & Kumar" films and the "Star Trek" reboot series.
  • E. Lee Byung-chul
    Lee Byung-chul was a South Korean entrepreneur and industrialist best known as the founder of the Samsung business empire, which grew into one of the world’s largest conglomerates.
  • 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_69d6ab4780948190bdb9f7620c2ac27e completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d9043bf0ec8190a51ef2641808320c completed April 10, 2026, 2:07 p.m.
NED1 Entity disambiguation (via context triple) batch_69f49dea043c8190a74ffb448bbae5d0 completed May 1, 2026, 12:34 p.m.
Created at: April 8, 2026, 9:47 p.m.