Triple
T20051556
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Seongdong District |
E499210
|
entity |
| Predicate | hasLandmark |
P105
|
FINISHED |
| Object |
Seoul Forest
Seoul Forest is a large urban park in Seoul featuring wooded areas, riverside walks, cultural spaces, and recreational facilities.
|
E1408192
|
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: Seoul Forest | Statement: [Seongdong District, hasLandmark, Seoul Forest]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Seoul Forest Context triple: [Seongdong District, hasLandmark, Seoul Forest]
-
A.
Seoul Land
Seoul Land is a major amusement park in Gwacheon, South Korea, featuring a variety of rides, themed zones, and family-friendly attractions.
-
B.
Seoul Special City
Seoul Special City is the capital and largest metropolis of South Korea, serving as the country’s political, economic, and cultural center.
-
C.
Gwangalli
Gwangalli is a coastal neighborhood in Busan, South Korea, best known for its sandy beach, vibrant nightlife, and scenic views of the nearby Gwangan Bridge.
-
D.
Dangsandong
Dangsandong is a neighborhood in Seoul, South Korea, known as a residential and commercial area within the city's southwestern region.
-
E.
Gwanaksan
Gwanaksan is a prominent mountain in the Seoul metropolitan area of South Korea, known for its hiking trails, rocky peaks, and scenic views over the surrounding cities.
- 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: Seoul Forest Triple: [Seongdong District, hasLandmark, Seoul Forest]
Generated description
Seoul Forest is a large urban park in Seoul featuring wooded areas, riverside walks, cultural spaces, and recreational facilities.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Seoul Forest Target entity description: Seoul Forest is a large urban park in Seoul featuring wooded areas, riverside walks, cultural spaces, and recreational facilities.
-
A.
Seoul Land
Seoul Land is a major amusement park in Gwacheon, South Korea, featuring a variety of rides, themed zones, and family-friendly attractions.
-
B.
Seoul Special City
Seoul Special City is the capital and largest metropolis of South Korea, serving as the country’s political, economic, and cultural center.
-
C.
Gwangalli
Gwangalli is a coastal neighborhood in Busan, South Korea, best known for its sandy beach, vibrant nightlife, and scenic views of the nearby Gwangan Bridge.
-
D.
Dangsandong
Dangsandong is a neighborhood in Seoul, South Korea, known as a residential and commercial area within the city's southwestern region.
-
E.
Gwanaksan
Gwanaksan is a prominent mountain in the Seoul metropolitan area of South Korea, known for its hiking trails, rocky peaks, and scenic views over the surrounding cities.
- 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_69da6276bcf48190aabbf279192a5fb4 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e6632ee4d48190b9de3a1efa064492 |
completed | April 20, 2026, 5:32 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a081607e4988190838907e8bce1ee3e |
completed | May 16, 2026, 7 a.m. |
| NEDg | Description generation | batch_6a081691dcfc8190b41040341d99a9c9 |
completed | May 16, 2026, 7:02 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a08171724cc81908d6997dbae84ad9e |
completed | May 16, 2026, 7:04 a.m. |
Created at: April 11, 2026, 3:38 p.m.