Triple

T19410810
Position Surface form Disambiguated ID Type / Status
Subject Blue Dragon Film Award E485580 entity
Predicate organizer P123 FINISHED
Object Sports Chosun E1374112 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: Sports Chosun | Statement: [Blue Dragon Film Award, organizer, Sports Chosun]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sports Chosun
Context triple: [Blue Dragon Film Award, organizer, Sports Chosun]
  • A. Sports Chosun chosen
    Sports Chosun is a South Korean sports and entertainment newspaper that organizes and oversees the prestigious Blue Dragon Film Awards.
  • B. KBL
    KBL is a Philippine political party founded by former president Ferdinand Marcos that played a dominant role during his authoritarian regime in the 1970s and 1980s.
  • C. KBL
    KBL is the IATA airport code for Hamid Karzai International Airport, the main international gateway serving Kabul, Afghanistan.
  • D. KBO
    KBO is a well-founded term ordering used in automated theorem proving and term rewriting systems to ensure termination of rewrite rules.
  • E. Naver Sports
    Naver Sports is a South Korean online sports portal operated by Naver that provides live scores, news, statistics, and multimedia coverage across a wide range of sports.
  • 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_69d8e8d5162481909db12435d9535c1a completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e62af4cc0c81909056b5e2ee574ab1 completed April 20, 2026, 1:32 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0733c9a8b88190b58f1d02d445426a completed May 15, 2026, 2:55 p.m.
Created at: April 10, 2026, 1:37 p.m.