Triple

T17399860
Position Surface form Disambiguated ID Type / Status
Subject Berg Castle E423056 entity
Predicate hasAlternativeName P39 FINISHED
Object Schloss Berg 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: Schloss Berg | Statement: [Berg Castle, hasAlternativeName, Schloss Berg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Schloss Berg
Context triple: [Berg Castle, hasAlternativeName, Schloss Berg]
  • A. Schloss Berg chosen
    Schloss Berg is a historic castle and former ducal residence located in the village of Berg in Bavaria, Germany, overlooking Lake Starnberg.
  • B. Schloss Niederaichbach
    Schloss Niederaichbach is a historic Bavarian castle and noble residence in Germany associated with European aristocratic families.
  • C. Schloss Neuenbürg
    Schloss Neuenbürg is a historic hilltop castle in the Black Forest region of Baden-Württemberg, Germany, now serving as a museum and cultural venue.
  • D. Schloss Weinheim
    Schloss Weinheim is a historic castle complex in the town of Weinheim, Germany, known for its picturesque architecture and surrounding parklands.
  • E. Schloss Johannisberg
    Schloss Johannisberg is a historic hilltop winery and former Benedictine monastery in Germany’s Rheingau region, renowned as one of the birthplaces of quality Riesling and late-harvest wines.
  • 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_69d889d710288190bf0f4762801fefae completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e43ac0596481908c400916d5c1b971 completed April 19, 2026, 2:15 a.m.
Created at: April 10, 2026, 5:45 a.m.