Triple
T10128648
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mangmi-dong |
E226278
|
entity |
| Predicate | romanization |
P2508
|
FINISHED |
| Object | Mangmi-dong |
E226278
|
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: Mangmi-dong | Statement: [Mangmi-dong, romanization, Mangmi-dong]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mangmi-dong Context triple: [Mangmi-dong, romanization, Mangmi-dong]
-
A.
Mangmi-dong
chosen
Mangmi-dong is a neighborhood in Busan, South Korea, known as a residential and commercial area within the city's Suyeong District.
-
B.
Ami-dong
Ami-dong is a neighborhood in Busan, South Korea, known in part for hosting a campus of Pusan National University.
-
C.
Millak-dong
Millak-dong is a coastal neighborhood in Busan, South Korea, known for its proximity to Gwangalli Beach and vibrant urban atmosphere.
-
D.
Umyeon-dong
Umyeon-dong is a neighborhood in southern Seoul, South Korea, known for its residential areas near Umyeon Mountain and its location within the affluent Gangnam region.
-
E.
Munrae-dong
Munrae-dong is a neighborhood in Seoul, South Korea, known for its blend of old industrial workshops, emerging art spaces, and trendy cafes.
- 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_69ca843057b48190a86730167f5d6b98 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cdd333186c819088bbf617967f24fa |
completed | April 2, 2026, 2:23 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69de8413f30c8190aebe1504e213b6cc |
completed | April 14, 2026, 6:14 p.m. |
Created at: March 30, 2026, 9:05 p.m.