Triple

T14372350
Position Surface form Disambiguated ID Type / Status
Subject KOSPI E356386 entity
Predicate comparedWith P278 FINISHED
Object KOSDAQ E375831 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: KOSDAQ | Statement: [KOSPI, comparedWith, KOSDAQ]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: KOSDAQ
Context triple: [KOSPI, comparedWith, KOSDAQ]
  • A. KOSDAQ Market chosen
    KOSDAQ Market is South Korea’s secondary stock market, specializing in the listing and trading of small and medium-sized growth and technology companies.
  • B. Korea Exchange (KRX)
    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.
  • C. KOSDAQ 150
    KOSDAQ 150 is a major South Korean stock market index that tracks the performance of 150 representative companies listed on the KOSDAQ market.
  • D. KOSPI
    KOSPI is South Korea’s main stock market index, tracking the performance of large companies listed on the Korea Exchange.
  • E. JASDAQ
    JASDAQ is a Japanese securities exchange market known primarily for listing emerging, venture, and small to mid-sized 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_69d8279163a081908aec45c0e3f1e02f completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de8fb2082c8190b42cc5f2bab4f574 completed April 14, 2026, 7:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd4c5363a081909681b54c1d8218dc completed May 8, 2026, 2:37 a.m.
Created at: April 10, 2026, 1:15 a.m.