Triple

T19116396
Position Surface form Disambiguated ID Type / Status
Subject 오세훈 E467917 entity
Predicate spouse P13 FINISHED
Object 송현옥
송현옥 is a South Korean academic and public figure known as the wife of Seoul Mayor Oh Se-hoon.
E1360353 NE FINISHED

How this triple was built (4 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: 송현옥 | Statement: [오세훈, spouse, 송현옥]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: 송현옥
Context triple: [오세훈, spouse, 송현옥]
  • A. Son Byeong-hui
    Son Byeong-hui was a prominent Korean religious and independence leader who modernized the Donghak movement into Cheondogyo and played a key role in the March 1st Movement against Japanese colonial rule.
  • B. Shin Hye-sook
    Shin Hye-sook is a South Korean figure skating coach best known for working with Olympic champion Yuna Kim during her early development.
  • C. Son Ki-jung
    Son Ki-jung was a Korean marathon runner who won the gold medal at the 1936 Berlin Olympics while competing for Japan under the name Son Kee-chung.
  • D. Kwak Sin-ae
    Kwak Sin-ae is a South Korean film producer best known for producing the Academy Award–winning film "Parasite."
  • E. Jo Yun-ok
    Jo Yun-ok is the wife of renowned Hong Kong martial artist, actor, and film director Sammo Hung.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: 송현옥
Triple: [오세훈, spouse, 송현옥]
Generated description
송현옥 is a South Korean academic and public figure known as the wife of Seoul Mayor Oh Se-hoon.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: 송현옥
Target entity description: 송현옥 is a South Korean academic and public figure known as the wife of Seoul Mayor Oh Se-hoon.
  • A. Suh Jin-suk
    Suh Jin-suk is a notable individual who prominently bears the Korean surname Suh.
  • B. Son Byeong-hui
    Son Byeong-hui was a prominent Korean religious and independence leader who modernized the Donghak movement into Cheondogyo and played a key role in the March 1st Movement against Japanese colonial rule.
  • C. Shin Hye-sook
    Shin Hye-sook is a South Korean figure skating coach best known for working with Olympic champion Yuna Kim during her early development.
  • D. Son Ki-jung
    Son Ki-jung was a Korean marathon runner who won the gold medal at the 1936 Berlin Olympics while competing for Japan under the name Son Kee-chung.
  • E. Kwak Sin-ae
    Kwak Sin-ae is a South Korean film producer best known for producing the Academy Award–winning film "Parasite."
  • F. None of above. chosen

Provenance (5 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_69d8dd06a26481908039e2a1bae8c597 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5e3984bf48190818fa2b01b75decb completed April 20, 2026, 8:28 a.m.
NED1 Entity disambiguation (via context triple) batch_6a05e66ffaf481909c31c007cb165147 completed May 14, 2026, 3:12 p.m.
NEDg Description generation batch_6a05e9cc2f90819082679876c6a713b5 completed May 14, 2026, 3:27 p.m.
NED2 Entity disambiguation (via description) batch_6a06ee0aa8748190bf2ac6740f47c591 completed May 15, 2026, 9:57 a.m.
Created at: April 10, 2026, 12:05 p.m.