Triple

T1848266
Position Surface form Disambiguated ID Type / Status
Subject Ammersee E41332 entity
Predicate hasIsland P970 FINISHED
Object Schwedeninsel
Schwedeninsel is a small, wooded island located in the Bavarian lake Ammersee in southern Germany.
 E221047 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: Schwedeninsel | Statement: [Ammersee, hasIsland, Schwedeninsel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Schwedeninsel
Context triple: [Ammersee, hasIsland, Schwedeninsel]
  • A. Ekerö Island
    Ekerö Island is a Swedish island in Lake Mälaren, known for its scenic landscapes and proximity to Stockholm.
  • B. Helgoland
    Helgoland is a small German archipelago in the North Sea known for its dramatic red sandstone cliffs, unique wildlife, and historical significance as a strategic naval and cultural site.
  • C. Öland
    Öland is Sweden’s second-largest island, known for its unique limestone plains, rich birdlife, and popular summer tourism along the Baltic Sea coast.
  • D. Rote Insel
    Rote Insel is a distinctive, historically working-class neighborhood in Berlin known for its island-like layout encircled by railway lines and its rich social and cultural history.
  • E. Lidingö
    Lidingö is a suburban island town in the Stockholm archipelago known for its affluent residential areas, natural landscapes, and proximity to Sweden’s capital.
  • 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: Schwedeninsel
Triple: [Ammersee, hasIsland, Schwedeninsel]
Generated description
Schwedeninsel is a small, wooded island located in the Bavarian lake Ammersee in southern Germany.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Schwedeninsel
Target entity description: Schwedeninsel is a small, wooded island located in the Bavarian lake Ammersee in southern Germany.
  • A. Ekerö Island
    Ekerö Island is a Swedish island in Lake Mälaren, known for its scenic landscapes and proximity to Stockholm.
  • B. Helgoland
    Helgoland is a small German archipelago in the North Sea known for its dramatic red sandstone cliffs, unique wildlife, and historical significance as a strategic naval and cultural site.
  • C. Öland
    Öland is Sweden’s second-largest island, known for its unique limestone plains, rich birdlife, and popular summer tourism along the Baltic Sea coast.
  • D. Rote Insel
    Rote Insel is a distinctive, historically working-class neighborhood in Berlin known for its island-like layout encircled by railway lines and its rich social and cultural history.
  • E. Lidingö
    Lidingö is a suburban island town in the Stockholm archipelago known for its affluent residential areas, natural landscapes, and proximity to Sweden’s capital.
  • 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_69a88648cd44819093303206d96d76ad completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69abb05412a08190855ea453d1264ea3 completed March 7, 2026, 4:57 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae030a0d3081908641c4a40e5b7700 completed March 8, 2026, 11:15 p.m.
NEDg Description generation batch_69ae037591a881908b353e0e8a8cc7ce completed March 8, 2026, 11:17 p.m.
NED2 Entity disambiguation (via description) batch_69ae03d69c808190810ca1de51552e8c completed March 8, 2026, 11:18 p.m.
Created at: March 4, 2026, 7:33 p.m.