Triple

T15812241
Position Surface form Disambiguated ID Type / Status
Subject Svetly E383382 entity
Predicate locatedWestOf P4239 FINISHED
Object Kaliningrad E19236 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: Kaliningrad | Statement: [Svetly, locatedWestOf, Kaliningrad]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kaliningrad
Context triple: [Svetly, locatedWestOf, Kaliningrad]
  • A. Königsberg
    Königsberg is a district or locality that forms part of the town of Braunfels in the German state of Hesse.
  • B. Königsberg chosen
    Königsberg was a historic Prussian city on the Baltic Sea, renowned as a major cultural and intellectual center of East Prussia and later known as Kaliningrad.
  • C. Tuapse
    Tuapse is a Black Sea port town in southern Russia known as a seaside resort and industrial center within Krasnodar Krai.
  • D. Konigsberg
    Konigsberg is a surname most famously associated with American filmmaker, writer, and comedian Woody Allen, whose birth name is Allan Stewart Konigsberg.
  • E. Kovrov
    Kovrov is an industrial city in western Russia known for its machine-building and arms manufacturing industries.
  • 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_69d86da2858c819090cc8481e7207b6e completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e0b52bbb888190b226567e84ced7e9 completed April 16, 2026, 10:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffbe66d78c81908308fc16c8d4e19c completed May 9, 2026, 11:08 p.m.
Created at: April 10, 2026, 4:49 a.m.