Triple

T14396261
Position Surface form Disambiguated ID Type / Status
Subject Alexander Aghassipour E356955 entity
Predicate coFoundedWith P2835 FINISHED
Object Mikkel Svane E356954 NE FINISHED

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: Mikkel Svane | Statement: [Alexander Aghassipour, coFoundedWith, Mikkel Svane]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mikkel Svane
Context triple: [Alexander Aghassipour, coFoundedWith, Mikkel Svane]
  • A. Mikkel Svane chosen
    Mikkel Svane is a Danish entrepreneur best known as the co-founder and longtime CEO of the customer service software company Zendesk.
  • B. Mikkel Bondesen
    Mikkel Bondesen is a television producer known for his executive production work on series such as "The Comedians."
  • C. Peter Høj
    Peter Høj is an Australian academic and university leader who has served as vice-chancellor at several major universities, including the University of Adelaide.
  • D. Jesper Nøhr
    Jesper Nøhr is a Danish software developer and entrepreneur best known for creating the code hosting platform Bitbucket.
  • E. Jens Toldstrup
    Jens Toldstrup was a prominent Danish resistance leader during World War II, known for organizing sabotage and intelligence operations against the German occupation.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d827927c988190ad98bb0360981783 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de90826f908190b3969af9b7cf922f completed April 14, 2026, 7:07 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd7a36382481909a39ba5e51084051 completed May 8, 2026, 5:52 a.m.
Created at: April 10, 2026, 1:17 a.m.