Triple

T22765680
Position Surface form Disambiguated ID Type / Status
Subject Battle of Craonne E563115 entity
Predicate CoalitionStrengthApprox P26187 FINISHED
Object about 30,000–40,000 troops 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: about 30,000–40,000 troops | Statement: [Battle of Craonne, CoalitionStrengthApprox, about 30,000–40,000 troops]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: CoalitionStrengthApprox
Context triple: [Battle of Craonne, CoalitionStrengthApprox, about 30,000–40,000 troops]
  • A. coalitionPotential
    Indicates the potential or likelihood that two or more entities can form a cooperative alliance or coalition.
  • B. coalitionLevel
    Indicates the degree or intensity of cooperative alignment or partnership between entities within a coalition.
  • C. unionStrengthApproximate chosen
    Indicates that the strength of a union or combination between entities is represented in an estimated or approximate manner rather than as an exact value.
  • D. strengthCoalition
    Indicates the degree to which a coalition is cohesive, influential, or capable of achieving its collective objectives.
  • E. largestCoalition
    Indicates that a given coalition is the largest (by size or defined measure) among all possible coalitions in the relevant 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_69e24552e11c81909c2d61578a558bd7 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17a80249c819091569e7b8d500b45 completed April 29, 2026, 3:26 a.m.
PD Predicate disambiguation batch_69eed2b88d88819096015deb6a648801 completed April 27, 2026, 3:06 a.m.
Created at: April 17, 2026, 3:26 p.m.