Triple
T5062204
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gyeonghuigung |
E114047
|
entity |
| Predicate | nativeName |
P15
|
FINISHED |
| Object | 경희궁 |
E114047
|
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: 경희궁 | Statement: [Gyeonghuigung, nativeName, 경희궁]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 경희궁 Context triple: [Gyeonghuigung, nativeName, 경희궁]
-
A.
Gyeongung Palace
Gyeongung Palace is the former name of Deoksugung, a historic royal palace in Seoul associated with the late Joseon dynasty and Korea’s imperial period.
-
B.
Changgyeonggung
Changgyeonggung is a historic Joseon Dynasty royal palace in central Seoul, known for its traditional Korean architecture, gardens, and role as a former residence of kings and queens.
-
C.
Gyeonghuigung
chosen
Gyeonghuigung is a historic Joseon Dynasty royal palace in central Seoul, known as one of the city's "Five Grand Palaces."
-
D.
Klaikangwon Palace
Klaikangwon Palace is a royal seaside residence in Hua Hin, Thailand, long associated with the Thai monarchy as a favored retreat.
-
E.
Hamnyeongjeon Hall
Hamnyeongjeon Hall is a royal residential hall within Deoksugung Palace in Seoul, historically used as the living quarters of Korea’s Emperor Gojong.
- 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_69bd443c0c8c81908663b77afb28e165 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd7475be3c819085cde8ec544c407e |
completed | March 20, 2026, 4:23 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bf330bc5c48190ad8ca1e413b6c68b |
completed | March 22, 2026, 12:08 a.m. |
Created at: March 20, 2026, 1:38 p.m.