Triple
T15427514
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Segyo-dong |
E369549
|
entity |
| Predicate | hasRomanization |
P2508
|
FINISHED |
| Object | Segyo-dong |
E369549
|
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: Segyo-dong | Statement: [Segyo-dong, hasRomanization, Segyo-dong]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Segyo-dong Context triple: [Segyo-dong, hasRomanization, Segyo-dong]
-
A.
Segyo-dong
chosen
Segyo-dong is a neighborhood (dong) within the city of Osan in Gyeonggi Province, South Korea.
-
B.
Seongho-dong
Seongho-dong is a neighborhood (dong) within the city of Osan in Gyeonggi Province, South Korea.
-
C.
Yongho-dong
Yongho-dong is a neighborhood in Busan, South Korea, known as a coastal residential area within the city's southern region.
-
D.
Samseong-dong
Samseong-dong is a prominent neighborhood in Seoul, South Korea, known for its upscale shopping, business centers, and major landmarks like COEX Mall.
-
E.
Nogosan-dong
Nogosan-dong is a neighborhood in Seoul, South Korea, known for its proximity to the bustling Sinchon area and its mix of residential streets and urban amenities.
- 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_69d85a1849f48190bf898068b2806fae |
completed | April 10, 2026, 2:02 a.m. |
| NER | Named-entity recognition | batch_69e03ec31f4881908b26ff7c381d7bc9 |
completed | April 16, 2026, 1:43 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a003c4303888190a93830ef534715ae |
completed | May 10, 2026, 8:05 a.m. |
Created at: April 10, 2026, 3:20 a.m.