Triple

T3787889
Position Surface form Disambiguated ID Type / Status
Subject Schloss Glienicke E85571 entity
Predicate locatedOn P40 FINISHED
Object River Havel E358205 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: River Havel | Statement: [Schloss Glienicke, locatedOn, River Havel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: River Havel
Context triple: [Schloss Glienicke, locatedOn, River Havel]
  • A. River Havel chosen
    The River Havel is a major waterway in northeastern Germany that flows through Berlin and Brandenburg, connecting several lakes and cities before joining the Elbe River.
  • B. River Ock
    River Ock is a small river in Oxfordshire, England, that flows through the Vale of White Horse before joining the River Thames.
  • C. River Leine
    The River Leine is a major river in central Germany that flows through the city of Hanover and several federal states before joining the Aller.
  • D. Unstrut River
    The Unstrut River is a tributary of the Saale in central Germany, flowing through Thuringia and Saxony-Anhalt and known for its scenic valleys, vineyards, and historic towns.
  • E. Weser
    The Weser is a major river in northwestern Germany that flows through several federal states before emptying into the North Sea.
  • 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_69aed937fa8881908208ef3801060826 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aee42e430081908d032dcdcef20fc5 completed March 9, 2026, 3:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4f05031cc8190825105f77dd76438 completed March 14, 2026, 5:21 a.m.
Created at: March 9, 2026, 3:13 p.m.