Triple

T18597487
Position Surface form Disambiguated ID Type / Status
Subject Aarhus South district E454529 entity
Predicate hasNeighborhood P40 FINISHED
Object Stavtrup
Stavtrup is a residential neighborhood in the southwestern part of Aarhus, Denmark, known for its suburban character and proximity to nature.
E1340227 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: Stavtrup | Statement: [Aarhus South district, hasNeighborhood, Stavtrup]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Stavtrup
Context triple: [Aarhus South district, hasNeighborhood, Stavtrup]
  • A. Blangsted
    Blangsted is a surname most notably associated with Folmar Blangsted, a film editor.
  • B. Tirstrup
    Tirstrup is a small village in eastern Jutland, Denmark, best known for hosting Aarhus Airport nearby.
  • C. Kværndrup
    Kværndrup is a small Danish village on the island of Funen, known for its proximity to the historic Egeskov Castle.
  • D. Tranekær
    Tranekær is a historic village on the Danish island of Langeland, known for its castle and scenic rural surroundings.
  • E. Ginnerup
    Ginnerup is a small village in Denmark best known as the birthplace of former Danish Prime Minister and NATO Secretary General Anders Fogh Rasmussen.
  • 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: Stavtrup
Triple: [Aarhus South district, hasNeighborhood, Stavtrup]
Generated description
Stavtrup is a residential neighborhood in the southwestern part of Aarhus, Denmark, known for its suburban character and proximity to nature.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Stavtrup
Target entity description: Stavtrup is a residential neighborhood in the southwestern part of Aarhus, Denmark, known for its suburban character and proximity to nature.
  • A. Blangsted
    Blangsted is a surname most notably associated with Folmar Blangsted, a film editor.
  • B. Tirstrup
    Tirstrup is a small village in eastern Jutland, Denmark, best known for hosting Aarhus Airport nearby.
  • C. Kværndrup
    Kværndrup is a small Danish village on the island of Funen, known for its proximity to the historic Egeskov Castle.
  • D. Tranekær
    Tranekær is a historic village on the Danish island of Langeland, known for its castle and scenic rural surroundings.
  • E. Ginnerup
    Ginnerup is a small village in Denmark best known as the birthplace of former Danish Prime Minister and NATO Secretary General Anders Fogh Rasmussen.
  • 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_69d8d38ae7e081908a98df1251842402 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e5474d934481909b4afd5ef9031c73 completed April 19, 2026, 9:21 p.m.
NED1 Entity disambiguation (via context triple) batch_6a053246930c8190b4bbdbd619e6e808 completed May 14, 2026, 2:24 a.m.
NEDg Description generation batch_6a0533de8c8c8190953cfacd5d9fe0b5 completed May 14, 2026, 2:30 a.m.
NED2 Entity disambiguation (via description) batch_6a0534a667508190bf2d32bc9894874f completed May 14, 2026, 2:34 a.m.
Created at: April 10, 2026, 11:44 a.m.