Triple

T14372051
Position Surface form Disambiguated ID Type / Status
Subject Lee Maeng-hee E356379 entity
Predicate relative P37 FINISHED
Object Lee Seo-hyun E1118669 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: Lee Seo-hyun | Statement: [Lee Maeng-hee, relative, Lee Seo-hyun]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lee Seo-hyun
Context triple: [Lee Maeng-hee, relative, Lee Seo-hyun]
  • A. Lee Seo-hyun chosen
    Lee Seo-hyun is a South Korean business executive and prominent member of the Samsung founding family, known for her leadership roles within Samsung Group affiliates.
  • B. Ahn Seo-hyun
    Ahn Seo-hyun is a South Korean actress best known internationally for her lead role in Bong Joon-ho’s film "Okja."
  • C. Jung Ho-yeon
    Jung Ho-yeon is a South Korean model-turned-actress who gained international fame for her breakout role in the Netflix survival drama series "Squid Game."
  • D. Han Kyu-seol
    Han Kyu-seol was a Korean official and diplomat involved in the negotiations surrounding the Japan–Korea Treaty of 1905, which marked a key step in Japan’s domination over Korea.
  • E. Park Geun-ryeong
    Park Geun-ryeong is a South Korean businesswoman and the younger sister of former South Korean president Park Geun-hye.
  • 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_69d8279163a081908aec45c0e3f1e02f completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de8fb2082c8190b42cc5f2bab4f574 completed April 14, 2026, 7:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe249ebd3c81908d8b562845d9ceb1 completed May 8, 2026, 5:59 p.m.
Created at: April 10, 2026, 1:15 a.m.