Triple

T22233999
Position Surface form Disambiguated ID Type / Status
Subject Haderslev Fjord E549540 entity
Predicate extendsToward P1673 FINISHED
Object Haderslev 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: Haderslev | Statement: [Haderslev Fjord, extendsToward, Haderslev]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Haderslev
Context triple: [Haderslev Fjord, extendsToward, Haderslev]
  • A. Haderslev chosen
    Haderslev is a historic town in southern Denmark known for its medieval cathedral, old town center, and role as a regional cultural and administrative hub.
  • B. Hellebæk
    Hellebæk is a coastal town in northeastern Zealand, Denmark, known for its scenic setting near Helsingør and its historic industrial and residential architecture.
  • C. Thisted
    Thisted is a coastal town and municipality in northwestern Jutland, Denmark, known for its scenic location by the Limfjord and its role as a regional commercial and cultural center.
  • D. Gladsaxe
    Gladsaxe is a municipality in the northern suburbs of Copenhagen, Denmark, known for its residential areas, green spaces, and role as part of the Greater Copenhagen urban region.
  • E. Næstved
    Næstved is a historic market town and commercial center in southern Denmark, located on the island of Zealand.
  • 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_69e11e4102b881909cf47d3768e25c19 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f12bf61504819093e70bee4c575d1c completed April 28, 2026, 9:51 p.m.
Created at: April 16, 2026, 8:38 p.m.