Triple

T22143836
Position Surface form Disambiguated ID Type / Status
Subject Songpa District E547233 entity
Predicate hasNotableNeighborhood P4813 FINISHED
Object Munjeong
Munjeong is a neighborhood in Seoul’s Songpa District known for its large outlet shopping area and modern residential developments.
 E1521994 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: Munjeong | Statement: [Songpa District, hasNotableNeighborhood, Munjeong]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Munjeong
Context triple: [Songpa District, hasNotableNeighborhood, Munjeong]
  • A. 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.
  • B. Seong-kyeong
    Seong-kyeong is a pregnant woman and one of the key survivors in the South Korean zombie thriller film "Train to Busan."
  • C. Maeng-hee
    Maeng-hee is a Korean given name, notably borne by individuals such as businessman Lee Maeng-hee.
  • D. Gyeongsun
    Gyeongsun was the last king of the Korean kingdom of Silla, ruling during its final years before annexation by Goryeo in the 10th century.
  • E. Byeong-gi
    Byeong-gi is a supporting character in the South Korean series "Squid Game," known as the doctor who secretly collaborates with corrupt guards to gain advantages in the deadly competition.
  • 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: Munjeong
Triple: [Songpa District, hasNotableNeighborhood, Munjeong]
Generated description
Munjeong is a neighborhood in Seoul’s Songpa District known for its large outlet shopping area and modern residential developments.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Munjeong
Target entity description: Munjeong is a neighborhood in Seoul’s Songpa District known for its large outlet shopping area and modern residential developments.
  • A. 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.
  • B. Seong-kyeong
    Seong-kyeong is a pregnant woman and one of the key survivors in the South Korean zombie thriller film "Train to Busan."
  • C. Maeng-hee
    Maeng-hee is a Korean given name, notably borne by individuals such as businessman Lee Maeng-hee.
  • D. Gyeongsun
    Gyeongsun was the last king of the Korean kingdom of Silla, ruling during its final years before annexation by Goryeo in the 10th century.
  • E. Byeong-gi
    Byeong-gi is a supporting character in the South Korean series "Squid Game," known as the doctor who secretly collaborates with corrupt guards to gain advantages in the deadly competition.
  • 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_69e11e3a95d88190a3bd80d9471976c3 completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f129c045448190b3d189cdb8c0d2fd completed April 28, 2026, 9:42 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0a96fe404481908a6b27dcf1406dfb completed May 18, 2026, 4:35 a.m.
NEDg Description generation batch_6a0a97e509a88190a7f316cf340d010a completed May 18, 2026, 4:39 a.m.
NED2 Entity disambiguation (via description) batch_6a0a987daa208190bab5b7adec1913e8 completed May 18, 2026, 4:41 a.m.
Created at: April 16, 2026, 8:32 p.m.