Triple

T20132535
Position Surface form Disambiguated ID Type / Status
Subject Gwanghwamun Station E490930 entity
Predicate near P350 FINISHED
Object Jogyesa Temple 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: Jogyesa Temple | Statement: [Gwanghwamun Station, near, Jogyesa Temple]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jogyesa Temple
Context triple: [Gwanghwamun Station, near, Jogyesa Temple]
  • A. Jogyesa Temple chosen
    Jogyesa Temple is a major Korean Buddhist temple in central Seoul, serving as the chief temple of the Jogye Order and a prominent cultural and religious landmark.
  • B. Maitreya Temple
    Maitreya Temple is a prominent Buddhist shrine within Thiksey Monastery in Ladakh, India, renowned for its large statue of Maitreya (the future Buddha) and intricate monastic artwork.
  • C. Sewu Temple
    Sewu Temple is a large 8th-century Buddhist temple complex in Central Java, Indonesia, renowned as one of the oldest and most significant religious monuments near the Prambanan area.
  • D. Ananda Temple
    Ananda Temple is a major 12th-century Buddhist temple in Bagan, Myanmar, renowned for its well-preserved architecture and richly decorated interior.
  • E. Gio-ji Temple
    Gio-ji Temple is a small, tranquil Buddhist temple in Kyoto renowned for its lush moss garden and serene forested setting.
  • 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_69da62651a0c8190a3e05e95e056a66b completed April 11, 2026, 3:01 p.m.
NER Named-entity recognition batch_69e66763ee908190af64af31b4ca2377 completed April 20, 2026, 5:50 p.m.
Created at: April 11, 2026, 11:31 p.m.