Triple

T21622918
Position Surface form Disambiguated ID Type / Status
Subject Jongno 1-ga E533621 entity
Predicate near P350 FINISHED
Object Jongno 3-ga 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: Jongno 3-ga | Statement: [Jongno 1-ga, near, Jongno 3-ga]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jongno 3-ga
Context triple: [Jongno 1-ga, near, Jongno 3-ga]
  • A. Jongno 3-ga chosen
    Jongno 3-ga is a central neighborhood in Seoul, South Korea, known for its traditional markets, jewelry shops, and vibrant mix of historic and cultural sites.
  • B. Jongno 2-ga
    Jongno 2-ga is a central neighborhood in Seoul, South Korea, known for its bustling commercial streets, traditional markets, and proximity to major historic and cultural sites.
  • C. Jongno 5-ga
    Jongno 5-ga is a neighborhood and subway station area in central Seoul, South Korea, known for its traditional markets, medical district, and proximity to historic Jongno Street.
  • D. Jongno 4-ga
    Jongno 4-ga is a neighborhood and subway station area in central Seoul, South Korea, known for its traditional markets, jewelry district, and proximity to historic Jongno Street.
  • E. Jongno 1-ga
    Jongno 1-ga is a central neighborhood in Seoul, South Korea, known for its historic streets, traditional markets, and proximity to major cultural and governmental landmarks.
  • 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_69e0c464fba881908d0ff2ac80511ce1 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ef3bb0c42c8190997fbeb7a764d60e completed April 27, 2026, 10:34 a.m.
Created at: April 16, 2026, 6:34 p.m.