Triple

T21660819
Position Surface form Disambiguated ID Type / Status
Subject Martwa Wisła E534588 entity
Predicate hasNameMeaning P1966 FINISHED
Object Dead Vistula 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: Dead Vistula | Statement: [Martwa Wisła, hasNameMeaning, Dead Vistula]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dead Vistula
Context triple: [Martwa Wisła, hasNameMeaning, Dead Vistula]
  • A. Dead Vistula chosen
    The Dead Vistula is a former main channel of Poland’s Vistula River near Gdańsk, now a regulated distributary important for local navigation and flood control.
  • B. Le Déluge (The Deluge)
    Le Déluge (The Deluge) is a dramatic 19th-century history painting by Swiss artist Charles Gleyre depicting the biblical flood in a highly emotional and romantic style.
  • C. Czarna Łada
    Czarna Łada is a river in southeastern Poland that flows through the town of Biłgoraj and forms part of the local drainage system of the region.
  • D. Waters of Death
    Waters of Death is a perilous, mythic boundary of lethal waters in the Epic of Gilgamesh that separates the mortal world from the distant realm of the gods.
  • E. Dar Pomorza
    Dar Pomorza is a historic Polish sailing frigate, now preserved as a museum ship and popular tourist attraction in Gdynia.
  • 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_69e0c467e1f48190af2650b19175abc4 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ef6c07bcb88190a9864672c20325ff completed April 27, 2026, 2 p.m.
Created at: April 16, 2026, 6:36 p.m.