Triple
T19598792
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 종묘 |
E470412
|
entity |
| Predicate | hangulName |
P17869
|
FINISHED |
| Object | 종묘 |
—
|
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: 종묘 | Statement: [종묘, hangulName, 종묘]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 종묘 Context triple: [종묘, hangulName, 종묘]
-
A.
종묘
chosen
종묘는 조선 왕조 역대 왕과 왕비의 신위를 모신 서울의 유네스코 세계문화유산으로, 한국 전통 건축과 제례 문화를 대표하는 유교 사당이다.
-
B.
Yeongdodaegyo
Yeongdodaegyo is a bascule bridge in Busan, South Korea, known as the city’s first mainland–island bridge and a local historical landmark.
-
C.
Donhwamun
Donhwamun is the main gate of Changdeokgung Palace in Seoul, South Korea, and one of the oldest surviving palace gates from the Joseon Dynasty.
-
D.
Gwangandaegyo
Gwangandaegyo is a prominent suspension bridge in Busan, South Korea, known for its scenic coastal views and nighttime LED light displays.
-
E.
Hyangak
Hyangak is a traditional Korean court and folk music style that developed indigenously on the Korean peninsula, distinct from imported musical forms.
- 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_69d8e510024481908415c0d616fa6186 |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e6407d46188190b9818665b2a698a5 |
completed | April 20, 2026, 3:04 p.m. |
Created at: April 10, 2026, 1:43 p.m.