Triple

T14645260
Position Surface form Disambiguated ID Type / Status
Subject Sundbyøster E343828 entity
Predicate sharesIslandWith P5790 FINISHED
Object Tårnby E1094147 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: Tårnby | Statement: [Sundbyøster, sharesIslandWith, Tårnby]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tårnby
Context triple: [Sundbyøster, sharesIslandWith, Tårnby]
  • A. Tårnby chosen
    Tårnby is a town on the island of Amager in eastern Denmark, forming part of the Copenhagen metropolitan area.
  • B. Hellerup
    Hellerup is a suburban district just north of central Copenhagen, known for its affluent residential areas, seaside location, and role as a key transport and commercial hub.
  • C. Herlev
    Herlev is a suburban municipality and town in the Capital Region of Denmark, located just northwest of central Copenhagen.
  • D. Ballerup
    Ballerup is a suburban municipality near Copenhagen in eastern Denmark, known for its residential areas, business parks, and sports facilities.
  • E. Birkerød
    Birkerød is a suburban town in northeastern Zealand, Denmark, known for its residential character, green surroundings, and proximity to Copenhagen.
  • 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_69d822e1a2cc81908e5bb93cf61ce3cc completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb4ea6d8481908e6331ca173c646b completed April 14, 2026, 9:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69ff3d379bc881908b7954c633787165 completed May 9, 2026, 1:57 p.m.
Created at: April 10, 2026, 1:26 a.m.