Triple

T17811905
Position Surface form Disambiguated ID Type / Status
Subject Cheongju E444728 entity
Predicate hasCulturalHeritage P3114 FINISHED
Object Heungdeoksa Temple Site NE NERFINISHED

How this triple was built (3 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: Heungdeoksa Temple Site | Statement: [Cheongju, hasCulturalHeritage, Heungdeoksa Temple Site]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Heungdeoksa Temple Site
Context triple: [Cheongju, hasCulturalHeritage, Heungdeoksa Temple Site]
  • A. Haedong Yonggungsa Temple
    Haedong Yonggungsa Temple is a scenic Buddhist temple in Busan, South Korea, renowned for its rare and dramatic location on rocky seaside cliffs overlooking the ocean.
  • B. Daereungwon Tomb Complex
    Daereungwon Tomb Complex is a large archaeological park in Gyeongju, South Korea, known for its numerous grass-covered royal burial mounds from the ancient Silla Kingdom.
  • C. Kumgangsan Temple
    Kumgangsan Temple is a historic Buddhist temple located in North Korea’s Mount Kumgang (Kumgangsan) region, known for its scenic mountain setting and cultural significance.
  • D. Jeondeungsa Temple
    Jeondeungsa Temple is a historic Buddhist temple in South Korea renowned for its ancient architecture, cultural relics, and scenic forested setting.
  • E. Bomunsa Temple
    Bomunsa Temple is a historic Buddhist temple on South Korea’s Ganghwa Island, known for its cliffside location, scenic sea views, and significant religious heritage.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Heungdeoksa Temple Site
Target entity description: Heungdeoksa Temple Site is an important historic Buddhist temple ruin in Cheongju, South Korea, renowned as the place where the world’s oldest extant metal movable-type printed book, the Jikji, was produced.
  • A. Haedong Yonggungsa Temple
    Haedong Yonggungsa Temple is a scenic Buddhist temple in Busan, South Korea, renowned for its rare and dramatic location on rocky seaside cliffs overlooking the ocean.
  • B. Daereungwon Tomb Complex
    Daereungwon Tomb Complex is a large archaeological park in Gyeongju, South Korea, known for its numerous grass-covered royal burial mounds from the ancient Silla Kingdom.
  • C. Kumgangsan Temple
    Kumgangsan Temple is a historic Buddhist temple located in North Korea’s Mount Kumgang (Kumgangsan) region, known for its scenic mountain setting and cultural significance.
  • D. Jeondeungsa Temple
    Jeondeungsa Temple is a historic Buddhist temple in South Korea renowned for its ancient architecture, cultural relics, and scenic forested setting.
  • E. Bomunsa Temple
    Bomunsa Temple is a historic Buddhist temple on South Korea’s Ganghwa Island, known for its cliffside location, scenic sea views, and significant religious heritage.
  • F. None of above. chosen

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_69d8b9f0de78819099395b14db75a8a6 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e4887b5e50819098506f0b92d709b5 completed April 19, 2026, 7:47 a.m.
Created at: April 10, 2026, 10:14 a.m.