Triple

T4581666
Position Surface form Disambiguated ID Type / Status
Subject Aarhus E101867 entity
Predicate hasLandmark P105 FINISHED
Object Dokk1
Dokk1 is a large modern public library and cultural center on Aarhus’s waterfront, known as one of the city’s key architectural and civic landmarks.
 E454511 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: Dokk1 | Statement: [Aarhus, hasLandmark, Dokk1]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Dokk1
Context triple: [Aarhus, hasLandmark, Dokk1]
  • A. Dok
    Dok is an ancient location associated with the Hasmonean leader Simon Thassi, known primarily as the site of his assassination.
  • B. Dokka
    Dokka is a small Norwegian town that serves as a local commercial and service center in the inland region of Oppland.
  • C. Dokkumer Ee
    Dokkumer Ee is a canalized waterway in the northern Netherlands that connects the town of Dokkum to the wider Frisian inland water network.
  • D. Dokkum
    Dokkum is a historic fortified town in the northern Netherlands, known as one of the Frisian Eleven Cities and for its association with the martyrdom of Saint Boniface.
  • E. Drongen
    Drongen is a district of the Belgian city of Ghent, known as a suburban area in East Flanders.
  • 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: Dokk1
Triple: [Aarhus, hasLandmark, Dokk1]
Generated description
Dokk1 is a large modern public library and cultural center on Aarhus’s waterfront, known as one of the city’s key architectural and civic landmarks.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Dokk1
Target entity description: Dokk1 is a large modern public library and cultural center on Aarhus’s waterfront, known as one of the city’s key architectural and civic landmarks.
  • A. Dok
    Dok is an ancient location associated with the Hasmonean leader Simon Thassi, known primarily as the site of his assassination.
  • B. Dokka
    Dokka is a small Norwegian town that serves as a local commercial and service center in the inland region of Oppland.
  • C. Dokkumer Ee
    Dokkumer Ee is a canalized waterway in the northern Netherlands that connects the town of Dokkum to the wider Frisian inland water network.
  • D. Dokkum
    Dokkum is a historic fortified town in the northern Netherlands, known as one of the Frisian Eleven Cities and for its association with the martyrdom of Saint Boniface.
  • E. Drongen
    Drongen is a district of the Belgian city of Ghent, known as a suburban area in East Flanders.
  • 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_69bd43d4ce208190b53158c882b222e3 completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd590116e88190b8495b2a78cf3fb6 completed March 20, 2026, 2:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69bde09015c48190b4f992f3f95023cf completed March 21, 2026, 12:04 a.m.
NEDg Description generation batch_69bde15983cc81909f188e17ca8f2f0b completed March 21, 2026, 12:07 a.m.
NED2 Entity disambiguation (via description) batch_69bde1fff7d08190ac2061a9c43d34d7 completed March 21, 2026, 12:10 a.m.
Created at: March 20, 2026, 1:10 p.m.