Triple

T17017769
Position Surface form Disambiguated ID Type / Status
Subject Yeouido Station E412865 entity
Predicate nearbyLandmark P350 FINISHED
Object Korea Exchange (KRX) Seoul office E231396 NE FINISHED

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: Korea Exchange (KRX) Seoul office | Statement: [Yeouido Station, nearbyLandmark, Korea Exchange (KRX) Seoul office]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Korea Exchange (KRX) Seoul office
Context triple: [Yeouido Station, nearbyLandmark, Korea Exchange (KRX) Seoul office]
  • A. Korea Exchange (KRX) chosen
    Korea Exchange (KRX) is South Korea’s main securities and derivatives exchange, providing a centralized marketplace for trading stocks, bonds, derivatives, and other financial instruments.
  • B. Seongbuk-gu Office
    Seongbuk-gu Office is the main local government building and administrative headquarters serving Seoul’s Seongbuk District.
  • C. KINTEX
    KINTEX is a major convention and exhibition center in Goyang, South Korea, known for hosting large-scale trade shows, conferences, and events.
  • D. Seocho-gu Office
    Seocho-gu Office is the main administrative government building and district office serving Seoul’s Seocho District.
  • E. KOSDAQ Market
    KOSDAQ Market is South Korea’s secondary stock market, specializing in the listing and trading of small and medium-sized growth and technology companies.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d886cc4170819093deddc7b8b4b6a7 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d480a58c8190a3912d26debb4311 completed April 18, 2026, 6:59 p.m.
NED1 Entity disambiguation (via context triple) batch_6a011b4d6cb881909b64b4368fd97fa9 completed May 10, 2026, 11:57 p.m.
Created at: April 10, 2026, 5:33 a.m.