Triple

T17718370
Position Surface form Disambiguated ID Type / Status
Subject Thun Castle E442264 entity
Predicate ownedBy P347 FINISHED
Object City of Thun NE NERFINISHED

How this triple was built (2 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: City of Thun | Statement: [Thun Castle, ownedBy, City of Thun]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: City of Thun
Context triple: [Thun Castle, ownedBy, City of Thun]
  • A. City of Lucerne
    The City of Lucerne is a historic Swiss city and member of the Old Swiss Confederacy, known for its strategic location by Lake Lucerne and its role in late medieval conflicts such as the Burgundian Wars.
  • B. City of Glarus
    The City of Glarus is a historic Swiss town and capital of the canton of Glarus, known for its role in late medieval conflicts and its picturesque Alpine setting.
  • C. Murten
    Murten is a historic bilingual town in the canton of Fribourg, Switzerland, known for its well-preserved medieval old town and lakeside setting on Lake Murten.
  • D. City of Zug
    The City of Zug is a historic Swiss city and canton capital in central Switzerland, known today as a low-tax financial hub and picturesque lakeside community.
  • E. Thun Old Town chosen
    Thun Old Town is the historic medieval center of Thun, Switzerland, known for its cobbled streets, riverside setting, and landmark hilltop castle.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8b9ec79688190b86bdcef85a7b3aa completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e474834aec81909ab7e8224c5a39d7 completed April 19, 2026, 6:21 a.m.
Created at: April 10, 2026, 10:06 a.m.