Triple

T17473528
Position Surface form Disambiguated ID Type / Status
Subject Konstantin Korovin E425477 entity
Predicate notableWork P4 FINISHED
Object Paris. Café de la Paix 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: Paris. Café de la Paix | Statement: [Konstantin Korovin, notableWork, Paris. Café de la Paix]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Paris. Café de la Paix
Context triple: [Konstantin Korovin, notableWork, Paris. Café de la Paix]
  • A. Paris Bar
    The Paris Bar is the professional association and regulatory body for lawyers practicing in Paris, France.
  • B. Paris Qualles
    Paris Qualles is an American television and film screenwriter and producer known for his work on socially conscious dramas and biographical projects.
  • C. Paris chosen
    Paris is the capital and largest city of France, renowned for its historic architecture, art, fashion, and cultural influence worldwide.
  • D. Paris
    Paris is a prince of Troy in Greek mythology, best known for judging the beauty contest of the goddesses and for abducting Helen, which sparked the Trojan War.
  • E. Paris
    Paris is a major Chilean department store and retail chain offering a wide range of apparel, home goods, and consumer products.
  • 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_69d889dbc2e88190b18ea6115e819258 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e451b990848190b2e8510d67e94b79 completed April 19, 2026, 3:53 a.m.
Created at: April 10, 2026, 5:47 a.m.