Triple

T22740861
Position Surface form Disambiguated ID Type / Status
Subject Haderslev Municipality E562407 entity
Predicate contains P35 FINISHED
Object Starup 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: Starup | Statement: [Haderslev Municipality, contains, Starup]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Starup
Context triple: [Haderslev Municipality, contains, Starup]
  • A. Starup chosen
    Starup is a small settlement in southern Denmark located near Haderslev Fjord in the Region of Southern Denmark.
  • B. StartUp (TV series)
    StartUp is a crime drama television series that follows a group of unlikely partners who launch a controversial digital currency startup amid the dangerous world of organized crime and corrupt law enforcement.
  • C. Startupland
    Startupland is a memoir and business book by Zendesk co-founder Mikkel Svane that chronicles the early struggles, growth, and lessons learned in building a global startup.
  • D. Startup.com
    Startup.com is a 2001 documentary film that chronicles the rise and fall of the dot-com startup GovWorks during the late-1990s internet boom.
  • E. Woodstock Ventures
    Woodstock Ventures is the company that organized and produced the iconic 1969 Woodstock Music & Art Fair and has since managed the festival’s brand and related projects.
  • 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_69e245513a5c81908d5cb471b4fc429d completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17972fde8819086094cea289a2af8 completed April 29, 2026, 3:22 a.m.
Created at: April 17, 2026, 3:23 p.m.