Triple

T11657031
Position Surface form Disambiguated ID Type / Status
Subject Skype E277035 entity
Predicate hasFounder P104 FINISHED
Object Janus Friis E56743 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: Janus Friis | Statement: [Skype, hasFounder, Janus Friis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Janus Friis
Context triple: [Skype, hasFounder, Janus Friis]
  • A. Janus Friis chosen
    Janus Friis is a Danish entrepreneur best known for co-founding the internet communications platform Skype.
  • B. Nikolaj Bjørner
    Nikolaj Bjørner is a computer scientist best known for his work on automated theorem proving and the development of the Z3 SMT solver.
  • C. George Edward Stenius
    George Edward Stenius, better known as George Seaton, was an American screenwriter, director, and producer noted for films such as "Miracle on 34th Street" and "Airport."
  • D. Mikkel E. G. Nielsen
    Mikkel E. G. Nielsen is a Danish film editor known for his work on acclaimed international films, including the war drama "Beasts of No Nation."
  • E. Andreas Mogensen
    Andreas Mogensen is a Danish engineer and astronaut with the European Space Agency, known as the first Dane to fly in space.
  • 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_69d6aafbb3c081908a9cdb4ecb8d981d completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8a3d0331481909682b2e504e4c9a0 completed April 10, 2026, 7:16 a.m.
NED1 Entity disambiguation (via context triple) batch_69f08fa01ba88190a4fa5a74fe96cfa9 completed April 28, 2026, 10:44 a.m.
Created at: April 8, 2026, 9:39 p.m.