Triple
T7373442
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jung-gu, Daejeon |
E170064
|
entity |
| Predicate | hasNameInLanguage |
P15
|
FINISHED |
| Object | 중구 (Korean) |
E170064
|
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: 중구 (Korean) | Statement: [Jung-gu, Daejeon, hasNameInLanguage, 중구 (Korean)]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 중구 (Korean) Context triple: [Jung-gu, Daejeon, hasNameInLanguage, 중구 (Korean)]
-
A.
중구
중구는 대한민국 대구광역시의 중심 상업·행정 지역으로, 번화한 도심과 역사·문화 시설이 밀집한 구이다.
-
B.
Jung-gu
chosen
Jung-gu is a central district of the metropolitan city of Daejeon in South Korea, known for its mix of commercial, residential, and administrative areas.
-
C.
Jung-gu
Jung-gu is a central administrative district of the metropolitan city of Ulsan in South Korea.
-
D.
Gwaebeop-dong
Gwaebeop-dong is a neighborhood in Busan, South Korea, known as an administrative subdivision of the city's Sasang District.
-
E.
Dong-gu
Dong-gu is an administrative district of the metropolitan city of Ulsan in South Korea, known for its coastal location and industrial facilities.
- 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_69c68a5bfaac81909ce7f001dfb70c76 |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f1a50898819087097a64e09e19eb |
completed | March 27, 2026, 9:07 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c802caa9988190bdc0ed5d5dd15979 |
completed | March 28, 2026, 4:33 p.m. |
Created at: March 27, 2026, 3:07 p.m.