Triple

T2654589
Position Surface form Disambiguated ID Type / Status
Subject Battle of Odessa (1941) E53977 entity
Predicate RomanianCasualtiesEstimate P6773 FINISHED
Object over 90,000 total casualties 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: over 90,000 total casualties | Statement: [Battle of Odessa (1941), RomanianCasualtiesEstimate, over 90,000 total casualties]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: RomanianCasualtiesEstimate
Context triple: [Battle of Odessa (1941), RomanianCasualtiesEstimate, over 90,000 total casualties]
  • A. militaryCasualtiesEstimate chosen
    Indicates an estimated number of people killed, wounded, or missing as a result of military conflict or operations.
  • B. PolishCasualties
    Indicates the number or extent of casualties suffered by Polish forces or population in a given conflict or event.
  • C. casualtiesEstimate
    Indicates an estimated number of people killed, injured, or otherwise harmed as a result of an event or incident.
  • D. FrenchCasualties
    Indicates that the relationship specifies the number or extent of casualties suffered by French forces in a given event or context.
  • E. numberOfGermanVictims
    Indicates the quantity of victims who are identified as German in the context of the described event or situation.
  • 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_69ab495e192081909c77b622e8e7e15a completed March 6, 2026, 9:38 p.m.
NER Named-entity recognition batch_69abda0ba2208190ad87763ecbef8c3c completed March 7, 2026, 7:55 a.m.
PD Predicate disambiguation batch_69abd815d06481909535c02b0aba8553 completed March 7, 2026, 7:47 a.m.
Created at: March 6, 2026, 9:53 p.m.