Triple

T1464950
Position Surface form Disambiguated ID Type / Status
Subject IJssel E27000 entity
Predicate passesThrough P225 FINISHED
Object Kampen E87640 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: Kampen | Statement: [IJssel, passesThrough, Kampen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kampen
Context triple: [IJssel, passesThrough, Kampen]
  • A. Kampen chosen
    Kampen is a historic Dutch city known for its well-preserved medieval center and riverside location in the province of Overijssel.
  • B. Strijen
    Strijen is a small town and former municipality located on the Hoeksche Waard island in the Dutch province of South Holland.
  • C. Battleground
    "Battleground" is a World War II drama film written by Paul Vogel that follows a besieged American infantry unit during the Battle of the Bulge.
  • D. Battle of the Nations
    The Battle of the Nations was a major 1813 Napoleonic War engagement near Leipzig in which a coalition of European powers decisively defeated Napoleon’s forces.
  • E. Guer
    Guer is a commune in the Morbihan department of Brittany in northwestern France, known for hosting France’s premier military academy, the École spéciale militaire de Saint-Cyr.
  • 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_69a496d25d6881909dbd84f86d763992 completed March 1, 2026, 7:43 p.m.
NER Named-entity recognition batch_69a4c5ba2d5c81909ee85713de961fcb completed March 1, 2026, 11:03 p.m.
NED1 Entity disambiguation (via context triple) batch_69ad0e7c8a608190b3ca574c118e89b5 completed March 8, 2026, 5:51 a.m.
Created at: March 1, 2026, 8:01 p.m.