Triple

T20347275
Position Surface form Disambiguated ID Type / Status
Subject Rossum E495903 entity
Predicate hasVariant P455 FINISHED
Object Van Rossum 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: Van Rossum | Statement: [Rossum, hasVariant, Van Rossum]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Van Rossum
Context triple: [Rossum, hasVariant, Van Rossum]
  • A. Johannes van Rossum
    Johannes van Rossum was a Dutch coachman and later companion closely associated with Princess Marianne of the Netherlands, with whom he had a long-term, controversial relationship.
  • B. Guido van Rossum chosen
    Guido van Rossum is a Dutch programmer best known as the creator of the Python programming language.
  • C. Lambert Meertens
    Lambert Meertens is a Dutch computer scientist known for his influential work in programming language design and formal methods.
  • D. Greg Ewing
    Greg Ewing is a computer scientist and software developer best known for creating Pyrex, an early language for writing Python C extensions more easily.
  • E. Sigismund Dijkstra
    Sigismund Dijkstra is a shrewd and influential spymaster and political operator from Andrzej Sapkowski’s Witcher universe, known for his intelligence, manipulation, and role in the power struggles of the Northern Kingdoms.
  • 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_69e0b4a3320881909495ae8bc30bc2dc completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e67839e7b48190876ce7133a20c65b completed April 20, 2026, 7:02 p.m.
Created at: April 16, 2026, 11:24 a.m.