Triple

T23158931
Position Surface form Disambiguated ID Type / Status
Subject Lörrach E578524 entity
Predicate locatedOnRiver P165 FINISHED
Object Wiese 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: Wiese | Statement: [Lörrach, locatedOnRiver, Wiese]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Wiese
Context triple: [Lörrach, locatedOnRiver, Wiese]
  • A. Wiese chosen
    The Wiese is a river in southwestern Germany that flows through the Black Forest region before joining the Rhine.
  • B. Wieseck
    Wieseck is a small river in the German state of Hesse that flows through the city of Giessen and its surrounding region.
  • C. Wiesenbach
    Wiesenbach is a small municipality in the Rhine-Neckar district of Baden-Württemberg in southwestern Germany.
  • D. Wiese River
    The Wiese River is a tributary of the Rhine flowing through parts of Germany and Switzerland, including the municipality of Riehen near Basel.
  • E. Wiese valley
    Wiese valley is a scenic valley in Germany’s Black Forest region, known for the Wiese River and its traditional villages and forested landscapes.
  • 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_69e245fc75348190a0288401044c8af8 completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f18efeddd48190b6d03d2146583dcc completed April 29, 2026, 4:54 a.m.
Created at: April 17, 2026, 4:02 p.m.