Triple

T2556628
Position Surface form Disambiguated ID Type / Status
Subject Niklas Zennström E56742 entity
Predicate founded P104 FINISHED
Object Joltid E277030 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: Joltid | Statement: [Niklas Zennström, founded, Joltid]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Joltid
Context triple: [Niklas Zennström, founded, Joltid]
  • A. Joltid chosen
    Joltid is a software company best known for developing peer-to-peer technologies that underpinned services like Skype.
  • B. Litovel
    Litovel is a historic town in the Olomouc Region of the Czech Republic, known for its traditional architecture and local brewery.
  • C. Jawz
    Jawz is the jaguar mascot representing Indiana University–Purdue University Indianapolis (IUPUI) at its athletic events and campus activities.
  • D. Eidolon
    Eidolon is an online classics journal and magazine that presents accessible, socially engaged writing on the ancient world for a broad contemporary audience.
  • E. Hallidie
    Hallidie is a surname most notably associated with Andrew Smith Hallidie, the 19th-century engineer credited with pioneering San Francisco’s cable car system.
  • 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_69ab4a4bfec081908039988ec4c86e28 completed March 6, 2026, 9:42 p.m.
NER Named-entity recognition batch_69abd310b3a48190b275be13eb050e57 completed March 7, 2026, 7:26 a.m.
NED1 Entity disambiguation (via context triple) batch_69af655f72fc81908a85a69f95d0b827 completed March 10, 2026, 12:27 a.m.
Created at: March 6, 2026, 9:48 p.m.