Triple

T29059228
Position Surface form Disambiguated ID Type / Status
Subject Prussian Field Army under Gebhard Leberecht von Blücher E735477 entity
Predicate flankAttack P70449 FINISHED
Object attacked the French right flank at Waterloo 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: attacked the French right flank at Waterloo | Statement: [Prussian Field Army under Gebhard Leberecht von Blücher, flankAttack, attacked the French right flank at Waterloo]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: flankAttack
Context triple: [Prussian Field Army under Gebhard Leberecht von Blücher, flankAttack, attacked the French right flank at Waterloo]
  • A. allianceFlank
    Indicates a cooperative maneuver where allied entities position themselves on the side of a common target or objective to gain a tactical advantage.
  • B. liesOnFlankOf
    Indicates that one entity is positioned along the side or lateral edge of another entity.
  • C. attackedFrom chosen
    Indicates that one entity initiated an attack against another entity originating from a specific source location or position.
  • D. counterattackBy
    Indicates that an entity launches a retaliatory attack in response to an initial attack carried out by another entity.
  • E. attackType
    Indicates the specific method, style, or category of attack used in an aggressive or hostile action between entities.
  • 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_69f077e85498819088b65186550da8cd completed April 28, 2026, 9:03 a.m.
NER Named-entity recognition batch_69f66095794c81909288f4255c47923f completed May 2, 2026, 8:37 p.m.
PD Predicate disambiguation batch_69f659d297cc8190b2b962ba30a1edb3 completed May 2, 2026, 8:08 p.m.
Created at: April 28, 2026, 10:14 a.m.