Triple

T20905609
Position Surface form Disambiguated ID Type / Status
Subject Gaegyeong E514789 entity
Predicate successor P78 FINISHED
Object Hanseong 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: Hanseong | Statement: [Gaegyeong, successor, Hanseong]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hanseong
Context triple: [Gaegyeong, successor, Hanseong]
  • A. Hanseong chosen
    Hanseong was the historical name for Seoul when it served as the capital of the Joseon Dynasty in Korea.
  • B. Tancheon
    Tancheon is a river in South Korea that flows through the city of Seongnam and serves as a key urban waterway and recreational area.
  • C. Kyongsong
    Kyongsong is a coastal town and county-level city in northeastern North Korea known for its hot springs and location along the Sea of Japan (East Sea).
  • D. Gwangmyeong
    Gwangmyeong is a city in South Korea known for its proximity to Seoul and attractions like the Gwangmyeong Cave, a former mine turned cultural and tourism complex.
  • E. Sinchon
    Sinchon is a vibrant university district in Seoul, South Korea, known for its dense concentration of colleges, youth culture, shopping, and nightlife.
  • 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_69e0b4f8a1108190bce3d31331290ced completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6e8ff36488190987ecdfcbed4220c completed April 21, 2026, 3:03 a.m.
Created at: April 16, 2026, 12:47 p.m.