Triple
T6563909
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bangudae Petroglyphs |
E153852
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object |
Daegok-ri
Daegok-ri is a locality in Ulsan, South Korea, best known as the site of the prehistoric Bangudae Petroglyphs.
|
E617199
|
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: Daegok-ri | Statement: [Bangudae Petroglyphs, locatedIn, Daegok-ri]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Daegok-ri Context triple: [Bangudae Petroglyphs, locatedIn, Daegok-ri]
-
A.
Taebong
Taebong was a short-lived Korean kingdom of the early 10th century that emerged during the Later Three Kingdoms period before being absorbed by Goryeo.
-
B.
Seo-dong
Seo-dong is a neighborhood within Busan’s Geumjeong District in South Korea, known primarily as a residential area with local commerce and community facilities.
-
C.
Nampo-dong
Nampo-dong is a bustling commercial and shopping district in central Busan, South Korea, known for its markets, street food, and proximity to the city’s harbor.
-
D.
Sokcho
Sokcho is a coastal city in northeastern South Korea known for its beaches, seafood, and proximity to Seoraksan National Park.
-
E.
Nopo-dong
Nopo-dong is a neighborhood in Busan, South Korea, known as a major transportation hub and gateway to the city.
- 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: Daegok-ri Triple: [Bangudae Petroglyphs, locatedIn, Daegok-ri]
Generated description
Daegok-ri is a locality in Ulsan, South Korea, best known as the site of the prehistoric Bangudae Petroglyphs.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Daegok-ri Target entity description: Daegok-ri is a locality in Ulsan, South Korea, best known as the site of the prehistoric Bangudae Petroglyphs.
-
A.
Taebong
Taebong was a short-lived Korean kingdom of the early 10th century that emerged during the Later Three Kingdoms period before being absorbed by Goryeo.
-
B.
Seo-dong
Seo-dong is a neighborhood within Busan’s Geumjeong District in South Korea, known primarily as a residential area with local commerce and community facilities.
-
C.
Nampo-dong
Nampo-dong is a bustling commercial and shopping district in central Busan, South Korea, known for its markets, street food, and proximity to the city’s harbor.
-
D.
Sokcho
Sokcho is a coastal city in northeastern South Korea known for its beaches, seafood, and proximity to Seoraksan National Park.
-
E.
Nopo-dong
Nopo-dong is a neighborhood in Busan, South Korea, known as a major transportation hub and gateway to the city.
- 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_69c6880cb35881909b763eb0125236b9 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6ae3a40488190892d20ca0d60b937 |
completed | March 27, 2026, 4:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7127fc0a081909589c2a05e457866 |
completed | March 27, 2026, 11:27 p.m. |
| NEDg | Description generation | batch_69c7130b4a788190978cbdc08e640fc0 |
completed | March 27, 2026, 11:30 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c713ead2a48190bbf95caf2ca8d997 |
completed | March 27, 2026, 11:34 p.m. |
Created at: March 27, 2026, 1:52 p.m.