Triple
T23218726
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kaeson Street |
E580822
|
entity |
| Predicate | hasNameInLanguage |
P15
|
FINISHED |
| Object | 개선거리 |
—
|
NE NERFINISHED |
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: 개선거리 | Statement: [Kaeson Street, hasNameInLanguage, 개선거리]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 개선거리 Context triple: [Kaeson Street, hasNameInLanguage, 개선거리]
-
A.
Yongbieocheonga
Yongbieocheonga is a 15th-century Korean poetic work, regarded as the first piece of literature written in Hangul and celebrating the founding and virtues of the Joseon dynasty.
-
B.
Korea Way
chosen
Korea Way is a vibrant stretch of Manhattan known for its dense concentration of Korean restaurants, shops, and cultural businesses, forming the core of New York City's Koreatown.
-
C.
Gimje
Gimje is a city in North Jeolla Province, South Korea, known for its expansive plains and agricultural production, particularly rice.
-
D.
Ghindae
Ghindae is a town in Eritrea located within the Northern Red Sea administrative region.
-
E.
Gengxin
Gengxin is a Chinese given name most notably borne by actor Lin Gengxin, known for his roles in popular Chinese films and television dramas.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e2460389408190be74f41d217799a9 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f191675de48190858907872a065c56 |
completed | April 29, 2026, 5:04 a.m. |
Created at: April 17, 2026, 4:08 p.m.