Triple

T10374183
Position Surface form Disambiguated ID Type / Status
Subject Rygge E244459 entity
Predicate locatedEastOf P4240 FINISHED
Object Mossesundet
Mossesundet is a strait in southeastern Norway that separates the town of Moss from the island of Jeløya.
E863647 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: Mossesundet | Statement: [Rygge, locatedEastOf, Mossesundet]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mossesundet
Context triple: [Rygge, locatedEastOf, Mossesundet]
  • A. Norrsundet
    Norrsundet is a small coastal locality in eastern Sweden known historically for its sawmill and harbor along the Gulf of Bothnia.
  • B. Brunnsviken
    Brunnsviken is a scenic bay in the Stockholm area of Sweden, known for its surrounding parks, recreational areas, and cultural landmarks.
  • C. Kalmarsund
    Kalmarsund is a strait in the Baltic Sea that separates the Swedish island of Öland from the mainland province of Småland.
  • D. Riddarfjärden
    Riddarfjärden is the easternmost bay of Lake Mälaren in central Stockholm, known for its iconic city skyline views and historic waterfront.
  • E. Askrikefjärden
    Askrikefjärden is a bay in the inner Stockholm archipelago in Sweden, known for its coastal landscapes and recreational boating waters.
  • 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: Mossesundet
Triple: [Rygge, locatedEastOf, Mossesundet]
Generated description
Mossesundet is a strait in southeastern Norway that separates the town of Moss from the island of Jeløya.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mossesundet
Target entity description: Mossesundet is a strait in southeastern Norway that separates the town of Moss from the island of Jeløya.
  • A. Norrsundet
    Norrsundet is a small coastal locality in eastern Sweden known historically for its sawmill and harbor along the Gulf of Bothnia.
  • B. Brunnsviken
    Brunnsviken is a scenic bay in the Stockholm area of Sweden, known for its surrounding parks, recreational areas, and cultural landmarks.
  • C. Kalmarsund
    Kalmarsund is a strait in the Baltic Sea that separates the Swedish island of Öland from the mainland province of Småland.
  • D. Riddarfjärden
    Riddarfjärden is the easternmost bay of Lake Mälaren in central Stockholm, known for its iconic city skyline views and historic waterfront.
  • E. Askrikefjärden
    Askrikefjärden is a bay in the inner Stockholm archipelago in Sweden, known for its coastal landscapes and recreational boating waters.
  • 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_69d381b3e328819094b23b8edcd29b5a completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4e9804e708190b15f5d38cac9c4c1 completed April 7, 2026, 11:24 a.m.
NED1 Entity disambiguation (via context triple) batch_69d87e6f30c88190992242b6e0c43581 completed April 10, 2026, 4:37 a.m.
NEDg Description generation batch_69d886c325c4819089dac35eb26e7961 completed April 10, 2026, 5:12 a.m.
NED2 Entity disambiguation (via description) batch_69d88dbbe97c8190861e08f3ff39f91b completed April 10, 2026, 5:42 a.m.
Created at: April 6, 2026, 12:02 p.m.