Triple

T22051574
Position Surface form Disambiguated ID Type / Status
Subject Poul Nyrup Rasmussen E544896 entity
Predicate precededBy P97 FINISHED
Object Poul Schlüter 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: Poul Schlüter | Statement: [Poul Nyrup Rasmussen, precededBy, Poul Schlüter]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Poul Schlüter
Context triple: [Poul Nyrup Rasmussen, precededBy, Poul Schlüter]
  • A. Poul Schlüter chosen
    Poul Schlüter was a Danish politician who served as Prime Minister of Denmark from 1982 to 1993 and led the Conservative People's Party.
  • B. Ole Meldgaard
    Ole Meldgaard is a screenwriter best known for co-writing the World War II survival film "Into the White."
  • C. Poul S. Christiansen
    Poul S. Christiansen was a Danish painter associated with the Funen Painters, known for his expressive landscapes and use of vibrant color.
  • D. Mogens Fog
    Mogens Fog was a Danish physician, communist politician, and prominent leader in the Danish resistance against Nazi occupation during World War II.
  • E. Poul Martin Møller
    Poul Martin Møller was a Danish philosopher, poet, and professor known for his influential contributions to Danish Romanticism and for mentoring the young Søren Kierkegaard.
  • 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_69e11e32445c8190ab97089b48a130bb completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f1283386f081908b70df81f38a5b1c completed April 28, 2026, 9:35 p.m.
Created at: April 16, 2026, 8:26 p.m.