Triple

T5966721
Position Surface form Disambiguated ID Type / Status
Subject Battle of Königsberg E132770 entity
Predicate germanCasualties P14574 FINISHED
Object tens of thousands killed or wounded LITERAL 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: tens of thousands killed or wounded | Statement: [Battle of Königsberg, germanCasualties, tens of thousands killed or wounded]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: germanCasualties
Context triple: [Battle of Königsberg, germanCasualties, tens of thousands killed or wounded]
  • A. numberOfGermanVictims chosen
    Indicates the quantity of victims who are identified as German in the context of the described event or situation.
  • B. casualtiesGermanWounded
    Indicates that the relationship specifies the number of German individuals who were wounded (but not killed) as casualties in a particular event or context.
  • C. AustrianCasualtiesApprox
    Indicates an approximate number or estimate of casualties suffered by Austrian forces or entities.
  • D. dutchCasualties
    Indicates that the relationship specifies the number or occurrence of casualties suffered by Dutch entities in a given event or context.
  • E. SwedishCasualties
    Indicates the number or extent of casualties suffered by Swedish forces or individuals in a given event or context.
  • F. None of above.

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_69c0086c2364819091e9fe2f58fa2517 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c03fb7f8a88190a8bd45208bda4a03 completed March 22, 2026, 7:15 p.m.
PD Predicate disambiguation batch_69c0335a635881909c58c1ef0f97f1e8 completed March 22, 2026, 6:22 p.m.
Created at: March 22, 2026, 4:03 p.m.