Triple

T17987044
Position Surface form Disambiguated ID Type / Status
Subject Adrian von Bubenberg E430262 entity
Predicate positionHeld P8 FINISHED
Object Schultheiss of Bern
Schultheiss of Bern was the chief magistrate and leading political authority of the medieval Swiss city-state of Bern.
E1300156 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: Schultheiss of Bern | Statement: [Adrian von Bubenberg, positionHeld, Schultheiss of Bern]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Schultheiss of Bern
Context triple: [Adrian von Bubenberg, positionHeld, Schultheiss of Bern]
  • A. Reto Schaerli
    Reto Schaerli is a Swiss film producer known for his work on the 2015 adaptation of "Heidi."
  • B. Thomas Hürlimann
    Thomas Hürlimann is a Swiss writer and playwright known for his novels, short stories, and stage works that often explore Swiss identity, history, and politics.
  • C. André Calmy
    André Calmy is the husband of Swiss politician and former President Micheline Calmy-Rey.
  • D. Rudolf Sprüngli-Ammann
    Rudolf Sprüngli-Ammann was a Swiss chocolatier and entrepreneur best known for building the family confectionery business into the renowned premium chocolate company Lindt & Sprüngli.
  • E. Heinrich Zurfluh
    Heinrich Zurfluh was a mountaineer known for participating in the first recorded ascent of Dykh-Tau in the Caucasus.
  • 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: Schultheiss of Bern
Triple: [Adrian von Bubenberg, positionHeld, Schultheiss of Bern]
Generated description
Schultheiss of Bern was the chief magistrate and leading political authority of the medieval Swiss city-state of Bern.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Schultheiss of Bern
Target entity description: Schultheiss of Bern was the chief magistrate and leading political authority of the medieval Swiss city-state of Bern.
  • A. Reto Schaerli
    Reto Schaerli is a Swiss film producer known for his work on the 2015 adaptation of "Heidi."
  • B. Thomas Hürlimann
    Thomas Hürlimann is a Swiss writer and playwright known for his novels, short stories, and stage works that often explore Swiss identity, history, and politics.
  • C. André Calmy
    André Calmy is the husband of Swiss politician and former President Micheline Calmy-Rey.
  • D. Rudolf Sprüngli-Ammann
    Rudolf Sprüngli-Ammann was a Swiss chocolatier and entrepreneur best known for building the family confectionery business into the renowned premium chocolate company Lindt & Sprüngli.
  • E. Heinrich Zurfluh
    Heinrich Zurfluh was a mountaineer known for participating in the first recorded ascent of Dykh-Tau in the Caucasus.
  • 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_69d8b90364248190a37381adea932f42 completed April 10, 2026, 8:46 a.m.
NER Named-entity recognition batch_69e4b29c6d0881909d450d2561d532a6 completed April 19, 2026, 10:46 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0337aae0d08190aef6a30f3a10eefc completed May 12, 2026, 2:22 p.m.
NEDg Description generation batch_6a033ca5e4c08190b7de8ab2d4fb8e3b completed May 12, 2026, 2:43 p.m.
NED2 Entity disambiguation (via description) batch_6a033daf5b948190926f2925b8e3cc84 completed May 12, 2026, 2:48 p.m.
Created at: April 10, 2026, 10:23 a.m.