Triple

T6563818
Position Surface form Disambiguated ID Type / Status
Subject Ulju-gun E153850 entity
Predicate hasCapital P204 FINISHED
Object Eonyang
Eonyang is a town in South Korea that serves as the administrative and commercial center of Ulju County in Ulsan.
 E606590 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: Eonyang | Statement: [Ulju-gun, hasCapital, Eonyang]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Eonyang
Context triple: [Ulju-gun, hasCapital, Eonyang]
  • A. Tanaeang
    Tanaeang is a village settlement located on the atoll of Tabiteuea in the island nation of Kiribati in the central Pacific Ocean.
  • B. Wiryeseong
    Wiryeseong was the first capital city of the ancient Korean kingdom of Baekje, located in the Han River basin near present-day Seoul.
  • C. Ungjin
    Ungjin was an ancient city in the Korean kingdom of Baekje that served as one of its historical capitals and a key political and cultural center.
  • D. Rodong
    Rodong is the abbreviated name of Rodong Sinmun, the official newspaper and primary propaganda outlet of North Korea’s ruling Workers’ Party.
  • E. Dong
    The Dong are an ethnic minority group in China, known for their distinctive wooden architecture, polyphonic folk singing, and concentration in the mountainous regions of southern China, including Guizhou Province.
  • 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: Eonyang
Triple: [Ulju-gun, hasCapital, Eonyang]
Generated description
Eonyang is a town in South Korea that serves as the administrative and commercial center of Ulju County in Ulsan.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Eonyang
Target entity description: Eonyang is a town in South Korea that serves as the administrative and commercial center of Ulju County in Ulsan.
  • A. Tanaeang
    Tanaeang is a village settlement located on the atoll of Tabiteuea in the island nation of Kiribati in the central Pacific Ocean.
  • B. Wiryeseong
    Wiryeseong was the first capital city of the ancient Korean kingdom of Baekje, located in the Han River basin near present-day Seoul.
  • C. Ungjin
    Ungjin was an ancient city in the Korean kingdom of Baekje that served as one of its historical capitals and a key political and cultural center.
  • D. Rodong
    Rodong is the abbreviated name of Rodong Sinmun, the official newspaper and primary propaganda outlet of North Korea’s ruling Workers’ Party.
  • E. Dong
    The Dong are an ethnic minority group in China, known for their distinctive wooden architecture, polyphonic folk singing, and concentration in the mountainous regions of southern China, including Guizhou Province.
  • 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_69c6880cb35881909b763eb0125236b9 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6ae3a40488190892d20ca0d60b937 completed March 27, 2026, 4:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6e42523848190b02682e6a640ac05 completed March 27, 2026, 8:10 p.m.
NEDg Description generation batch_69c6e50db2cc8190932c4d44257acb83 completed March 27, 2026, 8:14 p.m.
NED2 Entity disambiguation (via description) batch_69c6e5eacefc819092d0e9f79d90c4a6 completed March 27, 2026, 8:17 p.m.
Created at: March 27, 2026, 1:52 p.m.