Triple
T10567330
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pusanjin-gu |
E249383
|
entity |
| Predicate | hasSubdivision |
P747
|
FINISHED |
| Object | Bumseok-dong |
E913706
|
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: Bumseok-dong | Statement: [Pusanjin-gu, hasSubdivision, Bumseok-dong]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bumseok-dong Context triple: [Pusanjin-gu, hasSubdivision, Bumseok-dong]
-
A.
Bumseong-dong
chosen
Bumseong-dong is a neighborhood (dong) located within Pusanjin District in Busan, South Korea.
-
B.
Bumjin-dong
Bumjin-dong is a neighborhood (dong) located within Pusanjin District in Busan, South Korea.
-
C.
Sogyeok-dong
Sogyeok-dong is a neighborhood in central Seoul, South Korea, known for its traditional Korean houses (hanok), art galleries, and proximity to historic palaces.
-
D.
Beomil-dong
Beomil-dong is a neighborhood in Dong-gu, Busan, South Korea, known as a residential and commercial area within the city.
-
E.
Bupyeong-dong
Bupyeong-dong is a central neighborhood and administrative hub within Bupyeong District in Incheon, South Korea.
- 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_69d381c8bd708190acf3d275c908251e |
completed | April 6, 2026, 9:50 a.m. |
| NER | Named-entity recognition | batch_69d5272ef5848190b76d671ea2d26314 |
completed | April 7, 2026, 3:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e55621a88c8190b9611bf9e3b307de |
completed | April 19, 2026, 10:24 p.m. |
Created at: April 6, 2026, 12:36 p.m.