Triple

T17707847
Position Surface form Disambiguated ID Type / Status
Subject Wonsan-Kalma coastal area E441477 entity
Predicate transportConnection P1298 FINISHED
Object Wonsan port 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: Wonsan port | Statement: [Wonsan-Kalma coastal area, transportConnection, Wonsan port]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Wonsan port
Context triple: [Wonsan-Kalma coastal area, transportConnection, Wonsan port]
  • A. Wonsan Port chosen
    Wonsan Port is a major North Korean seaport on the east coast, serving as a key hub for maritime trade and naval operations in the city of Wonsan.
  • B. Sinuiju port
    Sinuiju port is a major North Korean river and trade port on the Yalu River, serving as a key hub for commerce and transport with neighboring China.
  • C. Nampo Port
    Nampo Port is a major North Korean seaport and industrial hub on the country’s west coast, serving as a key maritime gateway for trade and shipping.
  • D. Dangjin Port
    Dangjin Port is a major industrial and cargo seaport on South Korea’s west coast, serving as a key hub for steel, coal, and other bulk materials.
  • E. Chongjin port
    Chongjin port is a major industrial seaport in northeastern North Korea that serves as a key hub for maritime trade and heavy industry in the region.
  • 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_69d8b9ea20b48190ace88bb46b01e6a9 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e472990b5c81908e0414d3230f283e completed April 19, 2026, 6:13 a.m.
Created at: April 10, 2026, 10:05 a.m.