Triple

T5330180
Position Surface form Disambiguated ID Type / Status
Subject Allinge-Sandvig E123285 entity
Predicate hasPart P35 FINISHED
Object Sandvig
Sandvig is a coastal village on the northern tip of the Danish island of Bornholm, known for its scenic rocky shoreline and role as part of the twin town Allinge-Sandvig.
 E512639 NE FINISHED

How this triple was built (4 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: Sandvig | Statement: [Allinge-Sandvig, hasPart, Sandvig]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sandvig
Context triple: [Allinge-Sandvig, hasPart, Sandvig]
  • A. Svaneke
    Svaneke is a picturesque coastal town on the Danish island of Bornholm, known for its well-preserved half-timbered houses, harbor, and traditional smokehouses.
  • B. Solvang
    Solvang is a Danish-themed tourist town in California known for its Scandinavian architecture, bakeries, and wineries.
  • C. Merrild
    Merrild is a coffee brand and company known primarily in Northern Europe, offering a range of ground and whole-bean coffees.
  • D. Jette
    Jette is a municipality in the Brussels-Capital Region of Belgium, known for its residential character and educational institutions, including the Jette campus.
  • E. Solør
    Solør is a traditional district in Eastern Norway known for its rural landscapes, forestry, and agriculture.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Sandvig
Triple: [Allinge-Sandvig, hasPart, Sandvig]
Generated description
Sandvig is a coastal village on the northern tip of the Danish island of Bornholm, known for its scenic rocky shoreline and role as part of the twin town Allinge-Sandvig.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sandvig
Target entity description: Sandvig is a coastal village on the northern tip of the Danish island of Bornholm, known for its scenic rocky shoreline and role as part of the twin town Allinge-Sandvig.
  • A. Svaneke
    Svaneke is a picturesque coastal town on the Danish island of Bornholm, known for its well-preserved half-timbered houses, harbor, and traditional smokehouses.
  • B. Solvang
    Solvang is a Danish-themed tourist town in California known for its Scandinavian architecture, bakeries, and wineries.
  • C. Merrild
    Merrild is a coffee brand and company known primarily in Northern Europe, offering a range of ground and whole-bean coffees.
  • D. Jette
    Jette is a municipality in the Brussels-Capital Region of Belgium, known for its residential character and educational institutions, including the Jette campus.
  • E. Solør
    Solør is a traditional district in Eastern Norway known for its rural landscapes, forestry, and agriculture.
  • F. None of above. chosen

Provenance (5 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_69bd46477f9081909d242a327d749466 completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd859552d8819080758bdd7c43c66a completed March 20, 2026, 5:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf18b396c08190be60bcb9ac933b5e completed March 21, 2026, 10:16 p.m.
NEDg Description generation batch_69bf1b23cdbc8190bec3b7bc7f70770c completed March 21, 2026, 10:26 p.m.
NED2 Entity disambiguation (via description) batch_69bf1ba465948190aac6bfc406bae806 completed March 21, 2026, 10:28 p.m.
Created at: March 20, 2026, 2 p.m.