Triple
T20055654
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wiryeseong |
E499324
|
entity |
| Predicate | precedes |
P97
|
FINISHED |
| Object | Ungjin |
—
|
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: Ungjin | Statement: [Wiryeseong, precedes, Ungjin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ungjin Context triple: [Wiryeseong, precedes, Ungjin]
-
A.
Ungjin
chosen
Ungjin was an ancient city in the Korean kingdom of Baekje that served as one of its historical capitals and a key political and cultural center.
-
B.
Sokcho
Sokcho is a coastal city in northeastern South Korea known for its beaches, seafood, and proximity to Seoraksan National Park.
-
C.
Haeju
Haeju is a coastal city in southwestern North Korea, historically significant as a regional center and port on the Yellow Sea.
-
D.
Yŏngnŭng
Yŏngnŭng is the McCune–Reischauer romanization of Yeongneung, a royal tomb site in Paju, South Korea.
-
E.
Sareung
Sareung is a royal tomb in South Korea that forms part of the Donggureung cluster of Joseon Dynasty burial sites.
- 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_69da6276bcf48190aabbf279192a5fb4 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e66332b300819097f5dca1636e5822 |
completed | April 20, 2026, 5:32 p.m. |
Created at: April 11, 2026, 3:38 p.m.