Triple
T1398196
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Korean Air |
E30717
|
entity |
| Predicate | hasFocusCity |
P1295
|
FINISHED |
| Object | Jeju |
E105090
|
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: Jeju | Statement: [Korean Air, hasFocusCity, Jeju]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jeju Context triple: [Korean Air, hasFocusCity, Jeju]
-
A.
Jeju Island
chosen
Jeju Island is a volcanic South Korean resort island in the Korea Strait, famed for its natural scenery, mild climate, and popular tourist attractions.
-
B.
Ganghwa Island
Ganghwa Island is a historically significant and strategically located island off Korea’s west coast, known for its cultural heritage sites and role in past military conflicts.
-
C.
Yeongjong Island
Yeongjong Island is a major island off the coast of Incheon, South Korea, best known as the site of Incheon International Airport, the country’s primary international gateway.
-
D.
Neryungri
Neryungri is a major coal-mining and industrial city in southeastern Siberia, Russia, known as one of the key urban centers of the Sakha Republic (Yakutia).
-
E.
Ulsan
Ulsan is a major industrial city in southeastern South Korea, known for its large automobile, shipbuilding, and petrochemical complexes.
- 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_69a498fd4e408190bd73eca30ea9754c |
completed | March 1, 2026, 7:52 p.m. |
| NER | Named-entity recognition | batch_69a4c382b6588190833c39ac84fb6139 |
completed | March 1, 2026, 10:53 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad0e657d3c8190962220e52e3e64c0 |
completed | March 8, 2026, 5:51 a.m. |
Created at: March 1, 2026, 7:59 p.m.