Triple

T8850649
Position Surface form Disambiguated ID Type / Status
Subject Balhae E210628 entity
Predicate capital P234 FINISHED
Object Junggyeong
Junggyeong was one of the principal capital cities of the Balhae kingdom, serving as a key political and administrative center in Northeast Asia during the early medieval period.
 E761293 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: Junggyeong | Statement: [Balhae, capital, Junggyeong]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Junggyeong
Context triple: [Balhae, capital, Junggyeong]
  • A. Jinwicheon
    Jinwicheon is a river flowing through the city of Pyeongtaek in South Korea.
  • B. Hyeonreung
    Hyeonreung is a royal tomb from Korea’s Joseon Dynasty, notable as one of the UNESCO-listed burial sites of its kings and queens.
  • C. Uicheon
    Uicheon was an influential Korean Buddhist monk and scholar of the Goryeo dynasty, known for promoting the Cheontae (Tiantai) school and attempting to harmonize doctrinal and meditative traditions.
  • D. Seong Ga-yeong
    Seong Ga-yeong is the young daughter of protagonist Seong Gi-hun in the South Korean series "Squid Game."
  • E. Gwan-eum
    Gwan-eum is the Korean name for Guanyin, the bodhisattva of compassion widely revered in East Asian Buddhism.
  • 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: Junggyeong
Triple: [Balhae, capital, Junggyeong]
Generated description
Junggyeong was one of the principal capital cities of the Balhae kingdom, serving as a key political and administrative center in Northeast Asia during the early medieval period.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Junggyeong
Target entity description: Junggyeong was one of the principal capital cities of the Balhae kingdom, serving as a key political and administrative center in Northeast Asia during the early medieval period.
  • A. Jinwicheon
    Jinwicheon is a river flowing through the city of Pyeongtaek in South Korea.
  • B. Hyeonreung
    Hyeonreung is a royal tomb from Korea’s Joseon Dynasty, notable as one of the UNESCO-listed burial sites of its kings and queens.
  • C. Uicheon
    Uicheon was an influential Korean Buddhist monk and scholar of the Goryeo dynasty, known for promoting the Cheontae (Tiantai) school and attempting to harmonize doctrinal and meditative traditions.
  • D. Seong Ga-yeong
    Seong Ga-yeong is the young daughter of protagonist Seong Gi-hun in the South Korean series "Squid Game."
  • E. Gwan-eum
    Gwan-eum is the Korean name for Guanyin, the bodhisattva of compassion widely revered in East Asian Buddhism.
  • 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_69ca838a424c8190b1ecac115c2927e7 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc60c2300c819097b1ca6ebe2f749a completed April 1, 2026, 12:03 a.m.
NED1 Entity disambiguation (via context triple) batch_69cf89cb853c8190a7664f2e7de0de87 completed April 3, 2026, 9:35 a.m.
NEDg Description generation batch_69cf8ab7da348190b423f0768fe9dc1a completed April 3, 2026, 9:39 a.m.
NED2 Entity disambiguation (via description) batch_69cf8bd252a4819098891bbb67baf897 completed April 3, 2026, 9:43 a.m.
Created at: March 30, 2026, 6:49 p.m.