Triple

T23436256
Position Surface form Disambiguated ID Type / Status
Subject Gyeongseong Creature E563468 entity
Predicate settingPlace P1957 FINISHED
Object Gyeongseong 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: Gyeongseong | Statement: [Gyeongseong Creature, settingPlace, Gyeongseong]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gyeongseong
Context triple: [Gyeongseong Creature, settingPlace, Gyeongseong]
  • A. Gyeongseong chosen
    Gyeongseong was the Japanese colonial-era name for Seoul, which served as the administrative and political center of Korea under Japanese rule.
  • B. Sanggyeong
    Sanggyeong was the principal royal capital city of the Balhae kingdom, serving as its political and cultural center in Northeast Asia.
  • C. Cheong-seok
    Cheong-seok is a young Buddhist monk character in the South Korean supernatural horror film "The 8th Night," who becomes involved in a struggle against an ancient evil.
  • D. Ga-yeong
    Ga-yeong is a Korean feminine given name that can be borne by various real or fictional individuals.
  • E. Dongmyeong
    Dongmyeong is another name for Jumong, the legendary founder and first king of the ancient Korean kingdom of Goguryeo.
  • 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_69e24553980c8190bb66a2ae0bdab125 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f1a5dbdf248190a09e971f2718d01f completed April 29, 2026, 6:31 a.m.
Created at: April 17, 2026, 5:50 p.m.