Triple
T19540558
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sinsa-dong |
E488886
|
entity |
| Predicate | romanization |
P2508
|
FINISHED |
| Object |
Sinsa-tong (MR)
Sinsa-tong (MR) is the McCune–Reischauer romanization of Sinsa-dong, a neighborhood in Seoul, South Korea.
|
E1381103
|
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: Sinsa-tong (MR) | Statement: [Sinsa-dong, romanization, Sinsa-tong (MR)]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sinsa-tong (MR) Context triple: [Sinsa-dong, romanization, Sinsa-tong (MR)]
-
A.
Sinwonsa
Sinwonsa is a historic Buddhist temple in South Korea, known as one of the principal temples on Mount Gyeryong and noted for its traditional architecture and serene natural setting.
-
B.
Sinseongbong
Sinseongbong is a prominent mountain peak located within the Gyeryongsan mountain range in South Korea.
-
C.
Nonsan-si
Nonsan-si is a city in South Chungcheong Province, South Korea, known for its agricultural production and military training facilities.
-
D.
Sungsang
Sungsang is a coastal village in South Sumatra, Indonesia, known as a fishing and port settlement near the mouth of the Musi River.
-
E.
Sudogwon
Sudogwon is the Seoul Capital Area of South Korea, encompassing Seoul, Incheon, and surrounding Gyeonggi Province as the country’s largest and most populous metropolitan region.
- 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: Sinsa-tong (MR) Triple: [Sinsa-dong, romanization, Sinsa-tong (MR)]
Generated description
Sinsa-tong (MR) is the McCune–Reischauer romanization of Sinsa-dong, a neighborhood in Seoul, South Korea.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Sinsa-tong (MR) Target entity description: Sinsa-tong (MR) is the McCune–Reischauer romanization of Sinsa-dong, a neighborhood in Seoul, South Korea.
-
A.
Sinwonsa
Sinwonsa is a historic Buddhist temple in South Korea, known as one of the principal temples on Mount Gyeryong and noted for its traditional architecture and serene natural setting.
-
B.
Sinseongbong
Sinseongbong is a prominent mountain peak located within the Gyeryongsan mountain range in South Korea.
-
C.
Nonsan-si
Nonsan-si is a city in South Chungcheong Province, South Korea, known for its agricultural production and military training facilities.
-
D.
Sungsang
Sungsang is a coastal village in South Sumatra, Indonesia, known as a fishing and port settlement near the mouth of the Musi River.
-
E.
Sudogwon
Sudogwon is the Seoul Capital Area of South Korea, encompassing Seoul, Incheon, and surrounding Gyeonggi Province as the country’s largest and most populous metropolitan region.
- 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_69d8e8db5b6c8190984b61f91981f575 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e63872fda48190bbb1f465cb7b57fe |
completed | April 20, 2026, 2:30 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a074e8313048190ae949f99ff72d21a |
completed | May 15, 2026, 4:49 p.m. |
| NEDg | Description generation | batch_6a074ef599a88190a1edd95887a0c092 |
completed | May 15, 2026, 4:51 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a074fa5d4ec81908900ebf532408239 |
completed | May 15, 2026, 4:53 p.m. |
Created at: April 10, 2026, 1:41 p.m.