Triple

T1503645
Position Surface form Disambiguated ID Type / Status
Subject Tandberg E33850 entity
Predicate hasSubsidiaryOrDivision P25079 FINISHED
Object Tandberg Television E33850 NE FINISHED

How this triple was built (3 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: Tandberg Television | Statement: [Tandberg, hasSubsidiaryOrDivision, Tandberg Television]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tandberg Television
Context triple: [Tandberg, hasSubsidiaryOrDivision, Tandberg Television]
  • A. Tandberg chosen
    Tandberg is a Norwegian company best known for its video conferencing and telepresence solutions, which became part of Cisco Systems after its acquisition.
  • B. Biamp Systems
    Biamp Systems is an American professional audio and video equipment manufacturer known for its conferencing, signal processing, and networked media solutions used in commercial and institutional installations worldwide.
  • C. Ericsson
    Ericsson is a Swedish multinational telecommunications company known for providing mobile network infrastructure, services, and software to operators worldwide.
  • D. Control Video Corporation
    Control Video Corporation was an early 1980s technology company best known as the precursor to America Online (AOL), pioneering online services for home computer users.
  • E. NuvoMedia
    NuvoMedia was an early e-book technology company best known for creating the Rocket eBook, one of the first dedicated electronic book readers.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasSubsidiaryOrDivision
Context triple: [Tandberg, hasSubsidiaryOrDivision, Tandberg Television]
  • A. hasSubsidiaryLabel chosen
    Indicates that one entity is identified as a subsidiary or subordinate organization of another entity.
  • B. hasSubsidiaryTitle
    Indicates that an entity has an additional or secondary title formally associated with its main title.
  • C. hasBusinessDivision
    Indicates that an organization includes or is composed of a specific business division as a subordinate unit.
  • D. hasSubsidiaryHistory
    Indicates that an entity has a historical record of owning, controlling, or being associated with one or more subsidiary entities over time.
  • E. hasSubdivision
    Indicates that one entity is divided into and contains another entity as one of its constituent parts or administrative units.
  • F. None of above.

Provenance (4 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_69a885f352a4819099b24ff15489dede completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a90584b8b881908e112c7e59163812 completed March 5, 2026, 4:24 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad1cb578e4819082d254462e10e4f0 completed March 8, 2026, 6:52 a.m.
PD Predicate disambiguation batch_69a88727ce48819089b482cdc25453d1 completed March 4, 2026, 7:25 p.m.
Created at: March 4, 2026, 7:24 p.m.