Triple

T4872413
Position Surface form Disambiguated ID Type / Status
Subject Saltsjön E109114 entity
Predicate locatedNear P294 FINISHED
Object Kastellholmen
Kastellholmen is a small island in central Stockholm, Sweden, known for its historic red-brick citadel and scenic waterfront views.
 E491580 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: Kastellholmen | Statement: [Saltsjön, locatedNear, Kastellholmen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kastellholmen
Context triple: [Saltsjön, locatedNear, Kastellholmen]
  • A. Storholmen
    Storholmen is an island located in Lake Femunden, one of Norway’s largest inland lakes.
  • B. Stadsholmen
    Stadsholmen is the central island in Stockholm’s historic Gamla stan (Old Town), known for its medieval street layout and well-preserved architecture.
  • C. Skeppsholmen
    Skeppsholmen is a small central Stockholm island known for its historic naval heritage, museums, and scenic waterfront views.
  • D. Lindholmen
    Lindholmen is a waterfront district in Gothenburg, Sweden, known as a major hub for education, research, and technology companies.
  • E. Lindholmen
    Lindholmen is a small locality in Vallentuna Municipality in Stockholm County, Sweden, known for its residential character and proximity to natural and historical sites.
  • 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: Kastellholmen
Triple: [Saltsjön, locatedNear, Kastellholmen]
Generated description
Kastellholmen is a small island in central Stockholm, Sweden, known for its historic red-brick citadel and scenic waterfront views.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kastellholmen
Target entity description: Kastellholmen is a small island in central Stockholm, Sweden, known for its historic red-brick citadel and scenic waterfront views.
  • A. Storholmen
    Storholmen is an island located in Lake Femunden, one of Norway’s largest inland lakes.
  • B. Stadsholmen
    Stadsholmen is the central island in Stockholm’s historic Gamla stan (Old Town), known for its medieval street layout and well-preserved architecture.
  • C. Skeppsholmen
    Skeppsholmen is a small central Stockholm island known for its historic naval heritage, museums, and scenic waterfront views.
  • D. Lindholmen
    Lindholmen is a waterfront district in Gothenburg, Sweden, known as a major hub for education, research, and technology companies.
  • E. Lindholmen
    Lindholmen is a small locality in Vallentuna Municipality in Stockholm County, Sweden, known for its residential character and proximity to natural and historical sites.
  • 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_69bd440d96a48190b0c87069adef2af1 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd6d9e27908190a0c4540ee2559c4b completed March 20, 2026, 3:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69beb0cd44088190ba26171758898497 completed March 21, 2026, 2:53 p.m.
NEDg Description generation batch_69beb21e4b6c8190bf800ee885557323 completed March 21, 2026, 2:58 p.m.
NED2 Entity disambiguation (via description) batch_69beb23f789c8190811ee9e43327196c completed March 21, 2026, 2:59 p.m.
Created at: March 20, 2026, 1:27 p.m.