Triple

T23333623
Position Surface form Disambiguated ID Type / Status
Subject Střekov Castle E591513 entity
Predicate locatedOnRiver P165 FINISHED
Object Elbe River 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: Elbe River | Statement: [Střekov Castle, locatedOnRiver, Elbe River]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Elbe River
Context triple: [Střekov Castle, locatedOnRiver, Elbe River]
  • A. Elbe chosen
    The Elbe is one of Central Europe's major rivers, flowing from the Czech Republic through Germany to the North Sea and serving as an important waterway for transport, industry, and agriculture.
  • B. Saale
    The Saale is a major river in central Germany that flows through the states of Thuringia, Saxony-Anhalt, and Bavaria before joining the Elbe.
  • C. Elbe basin
    The Elbe basin is the extensive drainage area of the Elbe River in Central Europe, encompassing parts of Germany, the Czech Republic, and neighboring regions.
  • D. Weser
    The Weser is a major river in northwestern Germany that flows through several federal states before emptying into the North Sea.
  • E. Oder-Spree
    Oder-Spree is a rural district in the eastern German state of Brandenburg, known for its lakes, forests, and towns along the Oder and Spree rivers.
  • 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_69e25d20156c81908c5c53195bd9c738 completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f197efd98c819083635a2b8440f3eb completed April 29, 2026, 5:32 a.m.
Created at: April 17, 2026, 5:16 p.m.