Triple
T1351700
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ulsan |
E28895
|
entity |
| Predicate | borderedBy |
P224
|
FINISHED |
| Object |
Gyeongju
Gyeongju is a historic city in South Korea famed for its rich cultural heritage and numerous archaeological sites from the ancient Silla Kingdom.
|
E241549
|
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: Gyeongju | Statement: [Ulsan, borderedBy, Gyeongju]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gyeongju Context triple: [Ulsan, borderedBy, Gyeongju]
-
A.
Daegu
Daegu is a major metropolitan city in southeastern South Korea known for its textile industry, electronics manufacturing, and cultural festivals.
-
B.
Gwangju
Gwangju is a major metropolitan city in southwestern South Korea known for its rich cultural heritage and pivotal role in the country’s pro-democracy movement.
-
C.
Daejeon
Daejeon is a major city in central South Korea known as a hub for science, technology, and research institutions.
-
D.
Busan
Busan is South Korea’s second-largest city and a major international port known for its bustling harbor, beaches, and coastal scenery.
-
E.
Ulsan
Ulsan is a major industrial city in southeastern South Korea, known for its large automobile, shipbuilding, and petrochemical complexes.
- 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: Gyeongju Triple: [Ulsan, borderedBy, Gyeongju]
Generated description
Gyeongju is a historic city in South Korea famed for its rich cultural heritage and numerous archaeological sites from the ancient Silla Kingdom.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Gyeongju Target entity description: Gyeongju is a historic city in South Korea famed for its rich cultural heritage and numerous archaeological sites from the ancient Silla Kingdom.
-
A.
Daegu
Daegu is a major metropolitan city in southeastern South Korea known for its textile industry, electronics manufacturing, and cultural festivals.
-
B.
Gwangju
Gwangju is a major metropolitan city in southwestern South Korea known for its rich cultural heritage and pivotal role in the country’s pro-democracy movement.
-
C.
Daejeon
Daejeon is a major city in central South Korea known as a hub for science, technology, and research institutions.
-
D.
Busan
Busan is South Korea’s second-largest city and a major international port known for its bustling harbor, beaches, and coastal scenery.
-
E.
Ulsan
Ulsan is a major industrial city in southeastern South Korea, known for its large automobile, shipbuilding, and petrochemical complexes.
- 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_69a498571d248190a0ac9eb02d97097f |
completed | March 1, 2026, 7:49 p.m. |
| NER | Named-entity recognition | batch_69a4c26b1b4881908ae4b1b2c9b268a0 |
completed | March 1, 2026, 10:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae5d762bb0819092685731269e57c4 |
completed | March 9, 2026, 5:41 a.m. |
| NEDg | Description generation | batch_69ae5e1ea6108190b22ead618d620613 |
completed | March 9, 2026, 5:43 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ae5ea4edcc81908829e4bd64ce0aea |
completed | March 9, 2026, 5:46 a.m. |
Created at: March 1, 2026, 7:56 p.m.