Triple

T22571760
Position Surface form Disambiguated ID Type / Status
Subject Karlsruher SC E558089 entity
Predicate nickname P55 FINISHED
Object KSC 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: KSC | Statement: [Karlsruher SC, nickname, KSC]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: KSC
Context triple: [Karlsruher SC, nickname, KSC]
  • A. KSC
    KSC is the abbreviation for the Kosovo Specialist Chambers, a Hague-based court established to prosecute serious crimes related to the Kosovo conflict.
  • B. KSC
    KSC is the abbreviated name of the INTOSAI Knowledge Sharing and Knowledge Services Committee, a body focused on promoting the exchange and management of audit-related knowledge among supreme audit institutions worldwide.
  • C. KSC chosen
    KSC is a German football club based in Karlsruhe that competes in the country’s professional league system.
  • D. KSC
    KSC is the IATA airport code for Košice International Airport, the main commercial airport serving the city of Košice in eastern Slovakia.
  • E. KSC LC-39A
    KSC LC-39A is a historic launch pad at NASA’s Kennedy Space Center in Florida, used for major crewed missions from Apollo to SpaceX’s modern flights.
  • 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_69e11e5ae4ac8190b1f503457603d969 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15fae1ed881909430769a0015c39c completed April 29, 2026, 1:32 a.m.
Created at: April 16, 2026, 8:52 p.m.