Triple

T21623136
Position Surface form Disambiguated ID Type / Status
Subject Naksan E533626 entity
Predicate hangulName P17869 FINISHED
Object 낙산
낙산은 대한민국 강원도 양양군에 위치한 해안 산으로, 아름다운 일출과 낙산사로 유명한 관광 명소이다.
E1492898 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: 낙산 | Statement: [Naksan, hangulName, 낙산]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: 낙산
Context triple: [Naksan, hangulName, 낙산]
  • A. Seoraksan
    Seoraksan is a prominent and scenic mountain in northeastern South Korea, renowned for its dramatic granite peaks, vibrant autumn foliage, and status as part of a national park and UNESCO Biosphere Reserve.
  • B. Soreang
    Soreang is a suburban district and the administrative center of Bandung Regency in West Java, Indonesia, situated within the greater Bandung metropolitan area.
  • C. Yeongneung
    Yeongneung is a royal tomb complex in Yeoju, South Korea, that houses the burial site of King Sejong the Great and is part of the UNESCO-listed Royal Tombs of the Joseon Dynasty.
  • D. Yeongneung
    Yeongneung is a royal tomb site in Paju, South Korea, known as the burial place of King Jinjong and Queen Hyosun of the Joseon Dynasty.
  • E. Odaesan
    Odaesan is a prominent mountain in South Korea known for its scenic national park, rich biodiversity, and important Buddhist temples such as Woljeongsa.
  • 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: 낙산
Triple: [Naksan, hangulName, 낙산]
Generated description
낙산은 대한민국 강원도 양양군에 위치한 해안 산으로, 아름다운 일출과 낙산사로 유명한 관광 명소이다.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: 낙산
Target entity description: 낙산은 대한민국 강원도 양양군에 위치한 해안 산으로, 아름다운 일출과 낙산사로 유명한 관광 명소이다.
  • A. Seoraksan
    Seoraksan is a prominent and scenic mountain in northeastern South Korea, renowned for its dramatic granite peaks, vibrant autumn foliage, and status as part of a national park and UNESCO Biosphere Reserve.
  • B. Soreang
    Soreang is a suburban district and the administrative center of Bandung Regency in West Java, Indonesia, situated within the greater Bandung metropolitan area.
  • C. Yeongneung
    Yeongneung is a royal tomb complex in Yeoju, South Korea, that houses the burial site of King Sejong the Great and is part of the UNESCO-listed Royal Tombs of the Joseon Dynasty.
  • D. Yeongneung
    Yeongneung is a royal tomb site in Paju, South Korea, known as the burial place of King Jinjong and Queen Hyosun of the Joseon Dynasty.
  • E. Odaesan
    Odaesan is a prominent mountain in South Korea known for its scenic national park, rich biodiversity, and important Buddhist temples such as Woljeongsa.
  • 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_69e0c464fba881908d0ff2ac80511ce1 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ef3bb0c42c8190997fbeb7a764d60e completed April 27, 2026, 10:34 a.m.
NED1 Entity disambiguation (via context triple) batch_6a09fd4649ac8190bae1adba3110846b completed May 17, 2026, 5:39 p.m.
NEDg Description generation batch_6a09fe88fd24819097d222291bc63608 completed May 17, 2026, 5:44 p.m.
NED2 Entity disambiguation (via description) batch_6a09ff257c548190a7304bfee02dcbaf completed May 17, 2026, 5:47 p.m.
Created at: April 16, 2026, 6:34 p.m.