Triple

T15682852
Position Surface form Disambiguated ID Type / Status
Subject Leiden E377622 entity
Predicate locatedOn P40 FINISHED
Object New Rhine E103757 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: New Rhine | Statement: [Leiden, locatedOn, New Rhine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: New Rhine
Context triple: [Leiden, locatedOn, New Rhine]
  • A. High Rhine
    The High Rhine is a stretch of the Rhine River in Central Europe, flowing swiftly between Lake Constance and Basel and forming part of the border between Germany and Switzerland.
  • B. Rhens
    Rhens is a historic town on the Rhine River in western Germany, known for its medieval role as a meeting place of the prince-electors of the Holy Roman Empire.
  • C. Old Rhine chosen
    The Old Rhine is a historic branch of the Rhine River in the western Netherlands that flows through cities such as Leiden before reaching the North Sea.
  • D. RHINE
    RHINE is a pivotal phase III clinical trial evaluating faricimab for the treatment of diabetic macular edema.
  • E. Rhein II
    Rhein II is a large-scale color photograph by German visual artist Andreas Gursky, renowned for its minimalist depiction of the Rhine River and for once being the most expensive photograph ever sold at auction.
  • 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_69d85cd2e28481909d4e975bee20872f completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04f31b5b881908e46ecd9fc6048ab completed April 16, 2026, 2:53 a.m.
NED1 Entity disambiguation (via context triple) batch_6a008a1f8d648190b9c6280b875a17e4 completed May 10, 2026, 1:37 p.m.
Created at: April 10, 2026, 4:16 a.m.