Triple
T14089002
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jung District, Seoul |
E339072
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Cheonggyecheon |
E533618
|
NE FINISHED |
How this triple was built (2 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: Cheonggyecheon | Statement: [Jung District, Seoul, contains, Cheonggyecheon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cheonggyecheon Context triple: [Jung District, Seoul, contains, Cheonggyecheon]
-
A.
Cheonggyecheon Stream
chosen
Cheonggyecheon Stream is a restored urban waterway and public recreation space running through central Seoul, South Korea.
-
B.
Oncheoncheon Stream
Oncheoncheon Stream is an urban waterway in Busan, South Korea, known for its riverside parks, walking paths, and proximity to historic sites such as Geumjeong Fortress.
-
C.
Gayang-dong
Gayang-dong is a neighborhood in Gangseo District of Seoul, South Korea, known for its residential complexes and proximity to the Han River.
-
D.
Daegokcheon stream
Daegokcheon stream is a watercourse in Ulsan, South Korea, known for flowing past the Bangudae Petroglyphs, a major prehistoric rock art site.
-
E.
Anseongcheon
Anseongcheon is a river in South Korea that flows through the city of Pyeongtaek in Gyeonggi Province.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d81c687b0c819087fd9ed4198403f8 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de5ee1ce88819091c983286289337e |
completed | April 14, 2026, 3:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fcd0a5c9948190805c2e687c8809ff |
completed | May 7, 2026, 5:49 p.m. |
Created at: April 9, 2026, 10:21 p.m.