Triple

T474029
Position Surface form Disambiguated ID Type / Status
Subject Denikin offensive on Moscow E9020 entity
Predicate frontLineDirection P13445 FINISHED
Object from the south toward Moscow 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: from the south toward Moscow | Statement: [Denikin offensive on Moscow, frontLineDirection, from the south toward Moscow]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: frontLineDirection
Context triple: [Denikin offensive on Moscow, frontLineDirection, from the south toward Moscow]
  • A. frontLine
    Indicates that an entity is positioned at or associated with the foremost or primary line of engagement, activity, or defense relative to others.
  • B. frontSector
    Indicates that one entity is located in the forward-facing sector or region relative to another entity.
  • C. frontLineChange
    Indicates a change in the position or configuration of the primary boundary or leading edge between opposing sides.
  • D. frontType
    Indicates the type or category of a front (e.g., boundary or leading side) that one entity presents or forms relative to another.
  • E. front
    Indicates that one entity is located directly before or facing another entity along a primary viewing or movement direction.
  • F. None of above. chosen

Provenance (4 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_69a2e7ff81708190b0507a24a997232c completed Feb. 28, 2026, 1:05 p.m.
NER Named-entity recognition batch_69a2f0208c788190a96cdabcf593fda7 completed Feb. 28, 2026, 1:39 p.m.
PD Predicate disambiguation batch_69a2edeed31881908cf43beed410572d completed Feb. 28, 2026, 1:30 p.m.
PDg Predicate description generation batch_69a2eeba8a488190986cc7381332f783 completed Feb. 28, 2026, 1:33 p.m.
Created at: Feb. 28, 2026, 1:12 p.m.