Triple

T23299017
Position Surface form Disambiguated ID Type / Status
Subject Niklas Luhmann E590250 entity
Predicate familyName P18 FINISHED
Object Luhmann 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: Luhmann | Statement: [Niklas Luhmann, familyName, Luhmann]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Luhmann
Context triple: [Niklas Luhmann, familyName, Luhmann]
  • A. Niklas Luhmann chosen
    Niklas Luhmann was a German sociologist and social systems theorist known for developing a comprehensive theory of society based on the concept of self-referential social systems.
  • B. Lindtman
    Lindtman is a Finnish surname most notably borne by politician Antti Lindtman.
  • C. Heinz von Foerster (born Heinz von Foerster-Wolff)
    Heinz von Foerster (born Heinz von Foerster-Wolff) was an Austrian-American physicist and philosopher best known as a pioneer of cybernetics and second-order systems theory.
  • D. Lehmann
    Lehmann is a German-language surname borne by numerous notable individuals across fields such as science, politics, sports, and the arts.
  • E. Stafford Beer
    Stafford Beer was a British theorist and consultant who pioneered the application of cybernetics to management and organizational design, notably through his Viable System Model.
  • 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_69e25d1c0ecc8190a355aa229f06d0e0 completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f196d133448190bf350a9f51c1531c completed April 29, 2026, 5:27 a.m.
Created at: April 17, 2026, 5:03 p.m.