Triple

T10327422
Position Surface form Disambiguated ID Type / Status
Subject Prussian Navy E242794 entity
Predicate basedIn P40 FINISHED
Object Pillau E613662 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: Pillau | Statement: [Prussian Navy, basedIn, Pillau]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pillau
Context triple: [Prussian Navy, basedIn, Pillau]
  • A. Pillau chosen
    Pillau is a Baltic port town (now Baltiysk in Russia’s Kaliningrad Oblast) historically significant as a major evacuation point for German civilians and troops during the final months of World War II.
  • B. Kolberg
    Kolberg is a historic Baltic Sea port city in present-day Kołobrzeg, Poland, known for its strategic military importance and spa tourism.
  • C. Marienwerder
    Marienwerder is a historic town in former West Prussia, now known as Kwidzyn in Poland, noted for its medieval architecture and Teutonic Order castle.
  • D. Żory
    Żory is a city in southern Poland known for its historical roots in the Silesian region and its mix of industrial and residential character.
  • E. Nowogard
    Nowogard is a small town in northwestern Poland known for its historic architecture and surrounding lakes and forests.
  • 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_69d381af787481908bc401325c760a88 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4d7ce69b881909f27d97c90643634 completed April 7, 2026, 10:09 a.m.
NED1 Entity disambiguation (via context triple) batch_69d71dafa9308190ae0d3c34ba0c58b1 completed April 9, 2026, 3:31 a.m.
Created at: April 6, 2026, 11:51 a.m.