Triple

T23045629
Position Surface form Disambiguated ID Type / Status
Subject 류경호텔 E573869 entity
Predicate locatedIn P40 FINISHED
Object 평양 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: 평양 | Statement: [류경호텔, locatedIn, 평양]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: 평양
Context triple: [류경호텔, locatedIn, 평양]
  • A. Pyongyang chosen
    Pyongyang is the capital and largest city of North Korea, serving as its political, economic, and cultural center.
  • B. Sinuiju, Korea
    Sinuiju, Korea is a North Korean city on the Yalu River bordering China, known as an important industrial and transportation hub.
  • C. Pyeongyang
    Pyeongyang is the historic city that became the capital of the ancient Korean kingdom of Goguryeo and is now the capital of North Korea.
  • D. Wonsan
    Wonsan is a port city on North Korea’s east coast, known for its strategic military importance and role as a regional transportation and industrial hub.
  • E. Nampo
    Nampo is a major port city in southwestern North Korea, known for its industrial facilities and strategic location on the Yellow Sea.
  • 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_69e245b9c11481909d06c872214d21af completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f185192754819093a87d23371e7bbc completed April 29, 2026, 4:12 a.m.
Created at: April 17, 2026, 3:54 p.m.