Triple

T30565979
Position Surface form Disambiguated ID Type / Status
Subject École militaire interarmes E777976 entity
Predicate serviceBranchTarget P2099 FINISHED
Object French Army NE NERFINISHED

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: French Army | Statement: [École militaire interarmes, serviceBranchTarget, French Army]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: serviceBranchTarget
Context triple: [École militaire interarmes, serviceBranchTarget, French Army]
  • A. serviceBranch chosen
    Indicates the military or organizational branch in which an entity serves or is affiliated.
  • B. serviceBranchSpecific
    Indicates that something is restricted or tailored to a particular branch of service rather than being common across all branches.
  • C. serviceBranchLevel
    Indicates the hierarchical level or tier within a service branch at which an entity operates or is classified.
  • D. serviceBranchOptions
    Indicates the available branches or divisions of service that can be selected or associated with an entity.
  • E. serviceBranchFeature
    Indicates that a particular feature, capability, or characteristic is associated with or provided by a specific branch of service.
  • 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_69f2249ed41c8190b175170ecfd6e1c5 completed April 29, 2026, 3:32 p.m.
NER Named-entity recognition batch_69f791cc969c8190bf187d6031a030d5 completed May 3, 2026, 6:19 p.m.
PD Predicate disambiguation batch_69f791033d288190b118029fe412b9c9 completed May 3, 2026, 6:16 p.m.
Created at: April 29, 2026, 8:21 p.m.