Triple
T20498109
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kaesong |
E503225
|
entity |
| Predicate | historicalName |
P65
|
FINISHED |
| Object | Gaegyeong |
—
|
NE NERFINISHED |
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: Gaegyeong | Statement: [Kaesong, historicalName, Gaegyeong]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gaegyeong Context triple: [Kaesong, historicalName, Gaegyeong]
-
A.
Gaegyeong
chosen
Gaegyeong was the principal royal and administrative capital of the Korean kingdom of Goryeo, located in what is now Kaesong, North Korea.
-
B.
Gwangmu
Gwangmu was the era name associated with Emperor Gojong’s reign during Korea’s transition from the Joseon dynasty to the Korean Empire in the late 19th and early 20th centuries.
-
C.
Gyeongneung
Gyeongneung is a royal tomb within the Donggureung cluster in South Korea, serving as the burial site of members of the Joseon Dynasty.
-
D.
Kyongwon
Kyongwon is a county-level city in northeastern North Korea, located near the border with China in North Hamgyong Province.
-
E.
Seonjo
Seonjo was a Joseon dynasty king of Korea best known for his troubled reign during the late 16th century, including the devastating Japanese invasions led by Toyotomi Hideyoshi.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b4b1e52c8190894281cf7e3283ab |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e69cbefe4c819098af5bfd4d92341d |
completed | April 20, 2026, 9:38 p.m. |
Created at: April 16, 2026, 11:35 a.m.