Triple

T2919676
Position Surface form Disambiguated ID Type / Status
Subject Kungsholmen E78688 entity
Predicate hasNeighbourhood P4813 FINISHED
Object Marieberg
Marieberg is a small residential and institutional district on the island of Kungsholmen in central Stockholm, Sweden.
 E310296 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: Marieberg | Statement: [Kungsholmen, hasNeighbourhood, Marieberg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Marieberg
Context triple: [Kungsholmen, hasNeighbourhood, Marieberg]
  • A. Marienfelde
    Marienfelde is a locality in the southern part of Berlin known for its residential areas and historical refugee reception center.
  • B. Lilienthal
    Lilienthal is a German-origin surname borne by various notable individuals, including figures in aviation, science, and public service.
  • C. Neubukow
    Neubukow is a small town in northern Germany best known as the birthplace of archaeologist Heinrich Schliemann.
  • D. Lippendorf
    Lippendorf is a village in Saxony, Germany, historically notable as the birthplace of Katharina von Bora, the wife of Martin Luther.
  • E. Cölln
    Cölln was a historic town on the River Spree that, together with Berlin, formed the core of what later became the city of Berlin.
  • 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: Marieberg
Triple: [Kungsholmen, hasNeighbourhood, Marieberg]
Generated description
Marieberg is a small residential and institutional district on the island of Kungsholmen in central Stockholm, Sweden.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Marieberg
Target entity description: Marieberg is a small residential and institutional district on the island of Kungsholmen in central Stockholm, Sweden.
  • A. Marienfelde
    Marienfelde is a locality in the southern part of Berlin known for its residential areas and historical refugee reception center.
  • B. Lilienthal
    Lilienthal is a German-origin surname borne by various notable individuals, including figures in aviation, science, and public service.
  • C. Neubukow
    Neubukow is a small town in northern Germany best known as the birthplace of archaeologist Heinrich Schliemann.
  • D. Lippendorf
    Lippendorf is a village in Saxony, Germany, historically notable as the birthplace of Katharina von Bora, the wife of Martin Luther.
  • E. Cölln
    Cölln was a historic town on the River Spree that, together with Berlin, formed the core of what later became the city of Berlin.
  • 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_69ad8b0c2ad081909ff87050ae542bb9 completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad96a53f8c8190b188d549f1161e84 completed March 8, 2026, 3:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69b0562fc5f081909c9130f71f379a24 completed March 10, 2026, 5:34 p.m.
NEDg Description generation batch_69b06117ba088190886fa464f54525cd completed March 10, 2026, 6:21 p.m.
NED2 Entity disambiguation (via description) batch_69b0628d5f608190b7a13ac2e8b8d721 completed March 10, 2026, 6:27 p.m.
Created at: March 8, 2026, 2:54 p.m.