Triple

T12076623
Position Surface form Disambiguated ID Type / Status
Subject Berg E287565 entity
Predicate nobleTitle P914 FINISHED
Object Count of Berg E625679 NE FINISHED

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: Count of Berg | Statement: [Berg, nobleTitle, Count of Berg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Count of Berg
Context triple: [Berg, nobleTitle, Count of Berg]
  • A. Count of Berg chosen
    The Count of Berg was a medieval noble title held by the rulers of the County of Berg in the Holy Roman Empire, located in what is now western Germany.
  • B. Widdersberg
    Widdersberg is a small village that forms one of the local subdivisions of the municipality of Münsing in Bavaria, Germany.
  • C. Gerswalde
    Gerswalde is a small rural municipality in the Uckermark district of Brandenburg, northeastern Germany.
  • D. Count of Sulz
    The Count of Sulz was a historical noble title associated with a prominent aristocratic family in the Holy Roman Empire, later held by the influential House of Schwarzenberg.
  • E. Forchtenberg
    Forchtenberg is a small town in the German state of Baden-Württemberg, best known as the birthplace of anti-Nazi resistance figure Sophie Scholl.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d6ab4846e081908ee7bbd66a6d3459 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d9045ceeec81909427cae8972eed26 completed April 10, 2026, 2:08 p.m.
NED1 Entity disambiguation (via context triple) batch_69f5f660f48881908d50bf27b0892953 completed May 2, 2026, 1:04 p.m.
Created at: April 8, 2026, 9:48 p.m.