Triple

T8722039
Position Surface form Disambiguated ID Type / Status
Subject CEMAT E207033 entity
Predicate appliesToBranch P3304 FINISHED
Object Armée de terre E207024 NE 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: Armée de terre | Statement: [CEMAT, appliesToBranch, Armée de terre]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Armée de terre
Context triple: [CEMAT, appliesToBranch, Armée de terre]
  • A. Armée de terre chosen
    Armée de terre is the land warfare branch of the French Armed Forces, responsible for ground military operations.
  • B. Ejército de Tierra
    Ejército de Tierra is the land warfare branch of Spain’s Armed Forces, responsible for ground military operations and national defense.
  • C. État-major des armées
    État-major des armées is the central high command responsible for planning, directing, and coordinating all branches of the French Armed Forces.
  • D. Commandement des forces terrestres
    Commandement des forces terrestres is the French Army’s central command responsible for organizing, training, and preparing France’s land forces for operations.
  • E. Foreign Legion
    The Foreign Legion is an elite military unit of the French Armed Forces composed of volunteer soldiers from around the world, renowned for its rigorous training, strict discipline, and deployment in demanding overseas operations.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69ca835811d8819081ea00fd2a2c9a1c completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc5d0609f48190adc56226724b16c6 completed March 31, 2026, 11:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69cfdb7875448190a2478cbb623c31e6 completed April 3, 2026, 3:23 p.m.
Created at: March 30, 2026, 6:36 p.m.