Triple

T6686512
Position Surface form Disambiguated ID Type / Status
Subject North Gyeongsang Province E152110 entity
Predicate hasCity P316 FINISHED
Object Sangju
Sangju is a city in southeastern South Korea known historically for agriculture, particularly rice and dried persimmons, and for its role as a regional transport hub.
 E691673 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: Sangju | Statement: [North Gyeongsang Province, hasCity, Sangju]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sangju
Context triple: [North Gyeongsang Province, hasCity, Sangju]
  • A. Namyangju
    Namyangju is a city in South Korea known for its scenic natural landscapes, historical sites, and role as a suburban area within the Seoul metropolitan region.
  • B. Icheon
    Icheon is a South Korean city renowned for its traditional ceramics and hot spring resorts.
  • C. Gwangmyeong
    Gwangmyeong is a city in South Korea known for its proximity to Seoul and attractions like the Gwangmyeong Cave, a former mine turned cultural and tourism complex.
  • D. Gimcheon
    Gimcheon is a city in North Gyeongsang Province, South Korea, known as a regional transportation hub and administrative center.
  • E. Yeoju
    Yeoju is a city in South Korea known for its rich historical heritage, including royal tombs and ceramics, and its scenic riverside landscapes.
  • 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: Sangju
Triple: [North Gyeongsang Province, hasCity, Sangju]
Generated description
Sangju is a city in southeastern South Korea known historically for agriculture, particularly rice and dried persimmons, and for its role as a regional transport hub.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sangju
Target entity description: Sangju is a city in southeastern South Korea known historically for agriculture, particularly rice and dried persimmons, and for its role as a regional transport hub.
  • A. Namyangju
    Namyangju is a city in South Korea known for its scenic natural landscapes, historical sites, and role as a suburban area within the Seoul metropolitan region.
  • B. Icheon
    Icheon is a South Korean city renowned for its traditional ceramics and hot spring resorts.
  • C. Gwangmyeong
    Gwangmyeong is a city in South Korea known for its proximity to Seoul and attractions like the Gwangmyeong Cave, a former mine turned cultural and tourism complex.
  • D. Gimcheon
    Gimcheon is a city in North Gyeongsang Province, South Korea, known as a regional transportation hub and administrative center.
  • E. Yeoju
    Yeoju is a city in South Korea known for its rich historical heritage, including royal tombs and ceramics, and its scenic riverside landscapes.
  • 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_69c687f9977c819097e7f5ada4fe522e completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c6b14cd6748190aad4badd5f253478 completed March 27, 2026, 4:33 p.m.
NED1 Entity disambiguation (via context triple) batch_69c99ba1bbdc81909269ac0a97caa91d completed March 29, 2026, 9:37 p.m.
NEDg Description generation batch_69c99f9d6d988190b69500ae0a1b6f6c completed March 29, 2026, 9:54 p.m.
NED2 Entity disambiguation (via description) batch_69c9a057f37c8190837e56f60b1edb2e completed March 29, 2026, 9:57 p.m.
Created at: March 27, 2026, 2:04 p.m.