Triple
T21974654
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mansudae Assembly Hall |
E542672
|
entity |
| Predicate | officialName |
P66
|
FINISHED |
| Object |
만수대의사당
만수대의사당은 북한 평양에 위치한 최고인민회의가 열리는 대표적인 국가 의사당 건물이다.
|
E1511088
|
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: 만수대의사당 | Statement: [Mansudae Assembly Hall, officialName, 만수대의사당]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 만수대의사당 Context triple: [Mansudae Assembly Hall, officialName, 만수대의사당]
-
A.
Galmunwang Ipjong
Galmunwang Ipjong was a Silla royal prince and high-ranking noble of the Korean Three Kingdoms period, known primarily as a son of King Jinheung.
-
B.
Yeongdodaegyo
Yeongdodaegyo is a bascule bridge in Busan, South Korea, known as the city’s first mainland–island bridge and a local historical landmark.
-
C.
Garosu-gil
Garosu-gil is a trendy, tree-lined street in Seoul known for its fashionable boutiques, cafes, and vibrant youth culture.
-
D.
Gwan Gyeong
Gwan Gyeong was a historical Korean scholar-official known for helping compile the Samguk Sagi, one of the oldest surviving chronicles of Korea’s Three Kingdoms period.
-
E.
Jiphyeonjeon
Jiphyeonjeon was a royal research and advisory institute of the Joseon Dynasty, renowned as the scholarly center where King Sejong’s officials developed Hangul and advanced statecraft, science, and literature.
- 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: 만수대의사당 Triple: [Mansudae Assembly Hall, officialName, 만수대의사당]
Generated description
만수대의사당은 북한 평양에 위치한 최고인민회의가 열리는 대표적인 국가 의사당 건물이다.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: 만수대의사당 Target entity description: 만수대의사당은 북한 평양에 위치한 최고인민회의가 열리는 대표적인 국가 의사당 건물이다.
-
A.
Galmunwang Ipjong
Galmunwang Ipjong was a Silla royal prince and high-ranking noble of the Korean Three Kingdoms period, known primarily as a son of King Jinheung.
-
B.
Yeongdodaegyo
Yeongdodaegyo is a bascule bridge in Busan, South Korea, known as the city’s first mainland–island bridge and a local historical landmark.
-
C.
Garosu-gil
Garosu-gil is a trendy, tree-lined street in Seoul known for its fashionable boutiques, cafes, and vibrant youth culture.
-
D.
Gwan Gyeong
Gwan Gyeong was a historical Korean scholar-official known for helping compile the Samguk Sagi, one of the oldest surviving chronicles of Korea’s Three Kingdoms period.
-
E.
Jiphyeonjeon
Jiphyeonjeon was a royal research and advisory institute of the Joseon Dynasty, renowned as the scholarly center where King Sejong’s officials developed Hangul and advanced statecraft, science, and literature.
- 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_69e0c48070988190909db97667b9a0ac |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f12487a1a88190abb8a51fcd533b6a |
completed | April 28, 2026, 9:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0a671abb648190b9a4cc67c733f356 |
completed | May 18, 2026, 1:10 a.m. |
| NEDg | Description generation | batch_6a0a6812112c81909844ab725dff79ed |
completed | May 18, 2026, 1:14 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0a688613e8819081def9b6ba0d445e |
completed | May 18, 2026, 1:16 a.m. |
Created at: April 16, 2026, 8:03 p.m.