Triple

T18124469
Position Surface form Disambiguated ID Type / Status
Subject Treffurt E433833 entity
Predicate locatedOn P40 FINISHED
Object river Werra 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: river Werra | Statement: [Treffurt, locatedOn, river Werra]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: river Werra
Context triple: [Treffurt, locatedOn, river Werra]
  • A. Werra chosen
    The Werra is a major river in central Germany that forms one of the two headstreams of the Weser.
  • B. River Wiese
    The River Wiese is a river in southwestern Germany and northwestern Switzerland that flows through the Black Forest region before joining the Rhine near Basel.
  • C. Jagst
    The Jagst is a river in Baden-Württemberg, Germany, known as one of the major right-bank tributaries of the Neckar and flowing through a largely rural, scenic landscape.
  • D. Fulda River
    The Fulda River is a major river in central Germany that flows through the state of Hesse and joins the Werra River at Hann. Münden to form the Weser.
  • E. Schwalm River
    The Schwalm River is a waterway in the German state of Hesse that lends its name to the surrounding Schwalm-Eder region.
  • 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_69d8b909e8cc81908df4cc2b8ea6d11f completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4dded1bd4819080fa362e88c921cf completed April 19, 2026, 1:51 p.m.
Created at: April 10, 2026, 10:28 a.m.