Triple

T20770022
Position Surface form Disambiguated ID Type / Status
Subject Braunsberg E511202 entity
Predicate hasGermanName P1435 FINISHED
Object Braunsberg 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: Braunsberg | Statement: [Braunsberg, hasGermanName, Braunsberg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Braunsberg
Context triple: [Braunsberg, hasGermanName, Braunsberg]
  • A. Braunsberg chosen
    Braunsberg is a locality in former East Prussia (now in Poland) known for its proximity to the World War II Heiligenbeil pocket battlefield.
  • B. Bergneustadt
    Bergneustadt is a small town in North Rhine-Westphalia, Germany, known for its location in the hilly Oberbergischer Kreis region and its traditional half-timbered architecture.
  • C. Brockhagen
    Brockhagen is a village and district within the municipality of Steinhagen in the German state of North Rhine-Westphalia.
  • D. Osterburg
    Osterburg is a small town in the German state of Saxony-Anhalt, known for its historic architecture and rural surroundings.
  • E. Oberhaus
    The Oberhaus is the modern upper chamber of a bicameral legislature, functioning as the contemporary equivalent of the historical Erste Kammer.
  • 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_69e0b4ca01148190ac018e57e0cab46f completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c265f7dc8190a084e35d38d2783a completed April 21, 2026, 12:18 a.m.
Created at: April 16, 2026, 12:36 p.m.