Triple

T18951304
Position Surface form Disambiguated ID Type / Status
Subject Lewys E463656 entity
Predicate sharesEtymologyWith P28322 FINISHED
Object Louis 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: Louis | Statement: [Lewys, sharesEtymologyWith, Louis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Louis
Context triple: [Lewys, sharesEtymologyWith, Louis]
  • A. Louis
    Louis is the family name of Spyridon Louis, the Greek runner who won the first modern Olympic marathon in 1896.
  • B. Louis
    Louis is the given name of Louis Althusser, a prominent 20th-century French Marxist philosopher known for his structuralist interpretation of Marxism.
  • C. Louis
    Louis is the given first name of Lou Piniella, a former Major League Baseball outfielder and World Series–winning manager.
  • D. Louis
    Louis is one of the central introspective narrators in Virginia Woolf’s modernist novel "The Waves," known for his outsider status and poetic, self-analytical inner life.
  • E. Louis
    Louis was the personal name of Louis I, the first Grand Duke of Hesse, a 19th-century German ruler.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide. chosen

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_69d8dcffc278819086792a4ebfddfafa completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d54385e08190903a054681352d11 completed April 20, 2026, 7:26 a.m.
Created at: April 10, 2026, noon