Triple

T1498418
Position Surface form Disambiguated ID Type / Status
Subject 9th Division (Finland) E29738 entity
Predicate engagementOutcomeAtRaateRoad P18498 FINISHED
Object destruction of Soviet 44th Rifle Division 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: destruction of Soviet 44th Rifle Division | Statement: [9th Division (Finland), engagementOutcomeAtRaateRoad, destruction of Soviet 44th Rifle Division]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: engagementOutcomeAtRaateRoad
Context triple: [9th Division (Finland), engagementOutcomeAtRaateRoad, destruction of Soviet 44th Rifle Division]
  • A. engagementOutcome chosen
    Indicates the result or consequence produced by a particular engagement, interaction, or campaign between entities.
  • B. engagedBy
    Indicates that an entity is actively involved, occupied, or participating in an activity, process, or interaction initiated or provided by another entity.
  • C. onRoad
    Indicates that one entity is located on, traveling along, or otherwise situated upon a road.
  • D. engagementType
    Indicates the specific kind or category of engagement or interaction that occurs between the related entities.
  • E. engagementArea
    Indicates the spatial region or scope within which an entity’s actions, influence, or interactions are intended to occur.
  • 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_69a498dba1d8819093b46a3a8d2485f1 completed March 1, 2026, 7:51 p.m.
NER Named-entity recognition batch_69a4c6ef5ce88190a6b520525a6d42a3 completed March 1, 2026, 11:08 p.m.
PD Predicate disambiguation batch_69a4c48a8cf48190a6ebf8d44a608a06 completed March 1, 2026, 10:58 p.m.
Created at: March 1, 2026, 8:12 p.m.