Triple
T9812593
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Suyŏng-gu |
E238309
|
entity |
| Predicate | hasNameInKorean |
P17869
|
FINISHED |
| Object | 수영구 |
E698278
|
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: 수영구 | Statement: [Suyŏng-gu, hasNameInKorean, 수영구]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 수영구 Context triple: [Suyŏng-gu, hasNameInKorean, 수영구]
-
A.
북구
북구 is a Korean administrative district name commonly used for "Buk-gu" (North District) in various cities across South Korea.
-
B.
남구
남구는 대한민국 여러 도시에서 도심 남쪽에 위치한 행정구역(구)으로, 북구와 대칭되는 지리적·행정적 구분을 나타내는 명칭이다.
-
C.
Suyeong-gu
chosen
Suyeong-gu is a coastal district in the city of Busan, South Korea, known for its urban neighborhoods and proximity to popular beaches.
-
D.
Dongnae District
Dongnae District is a historic and central administrative district of Busan, South Korea, known for its hot springs and cultural heritage sites.
-
E.
Cijin District
Cijin District is a coastal district of Kaohsiung, Taiwan, known for its historic port, seafood markets, and popular seaside attractions.
- 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_69ca84defac48190abc1148804f184c1 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdb222ba788190a9085272a3de7852 |
completed | April 2, 2026, 12:02 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1cc63c450819091e57030a48e7d88 |
completed | April 5, 2026, 2:43 a.m. |
Created at: March 30, 2026, 8:30 p.m.