Triple

T5046489
Position Surface form Disambiguated ID Type / Status
Subject Thun E113677 entity
Predicate hasLandmark P105 FINISHED
Object Scherzligen Church
Scherzligen Church is a historic lakeside church in Thun, Switzerland, known for its medieval architecture and scenic setting on the shores of Lake Thun.
E489596 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: Scherzligen Church | Statement: [Thun, hasLandmark, Scherzligen Church]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Scherzligen Church
Context triple: [Thun, hasLandmark, Scherzligen Church]
  • A. Gemarke Church
    Gemarke Church is a notable Christian church located in the Barmen district of Wuppertal, Germany.
  • B. Lamaria Church
    Lamaria Church is a historic medieval Georgian Orthodox church overlooking the village of Ushguli in the mountainous Svaneti region of Georgia.
  • C. Talgje Church
    Talgje Church is a historic parish church located on the island of Talgje in Rogaland county, Norway.
  • D. Stoolbend Church
    Stoolbend Church is a local place of worship serving the community of Stoolbend, Virginia.
  • E. St. Urbanus Church
    St. Urbanus Church is a prominent Roman Catholic church in Ouderkerk aan de Amstel, Netherlands, known for its neo-Gothic architecture designed by Pierre Cuypers.
  • 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: Scherzligen Church
Triple: [Thun, hasLandmark, Scherzligen Church]
Generated description
Scherzligen Church is a historic lakeside church in Thun, Switzerland, known for its medieval architecture and scenic setting on the shores of Lake Thun.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Scherzligen Church
Target entity description: Scherzligen Church is a historic lakeside church in Thun, Switzerland, known for its medieval architecture and scenic setting on the shores of Lake Thun.
  • A. Gemarke Church
    Gemarke Church is a notable Christian church located in the Barmen district of Wuppertal, Germany.
  • B. Lamaria Church
    Lamaria Church is a historic medieval Georgian Orthodox church overlooking the village of Ushguli in the mountainous Svaneti region of Georgia.
  • C. Talgje Church
    Talgje Church is a historic parish church located on the island of Talgje in Rogaland county, Norway.
  • D. Stoolbend Church
    Stoolbend Church is a local place of worship serving the community of Stoolbend, Virginia.
  • E. St. Urbanus Church
    St. Urbanus Church is a prominent Roman Catholic church in Ouderkerk aan de Amstel, Netherlands, known for its neo-Gothic architecture designed by Pierre Cuypers.
  • 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_69bd44391fc48190a311ce9c826c209b completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd73fe99688190961708f5d8eb6bff completed March 20, 2026, 4:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69bea47e5ba0819088217a9ad3ce2b0a completed March 21, 2026, 2 p.m.
NEDg Description generation batch_69bea555c0548190a3be6d73f0319064 completed March 21, 2026, 2:04 p.m.
NED2 Entity disambiguation (via description) batch_69bea5daac00819083d142a56fa1b5fe completed March 21, 2026, 2:06 p.m.
Created at: March 20, 2026, 1:37 p.m.