Triple

T31329024
Position Surface form Disambiguated ID Type / Status
Subject General council of France E798973 entity
Predicate couldLevy P41654 FINISHED
Object local taxes 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: local taxes | Statement: [General council of France, couldLevy, local taxes]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: couldLevy
Context triple: [General council of France, couldLevy, local taxes]
  • A. canLevy chosen
    Indicates that an entity has the authority or power to impose and collect a charge, tax, or fine on another entity or resource.
  • B. canElect
    Indicates that one entity has the authority or ability to choose another entity for a position, role, or office through an election process.
  • C. couldPass
    Indicates that one entity had the ability or potential to move through, overcome, or be accepted by another entity or barrier.
  • D. canRaise
    Indicates that one entity has the ability or authority to increase, elevate, or lift another entity (such as a value, object, or status).
  • E. canLeadTo
    Indicates that one entity, condition, or event has the potential to cause, result in, or bring about another.
  • 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_69f224e3238c8190b2291f50ea4962cd completed April 29, 2026, 3:33 p.m.
NER Named-entity recognition batch_69f69ede2ea48190999b3d041f7bf55e completed May 3, 2026, 1:03 a.m.
PD Predicate disambiguation batch_69f69d1d25e88190a7f57d323574da90 completed May 3, 2026, 12:55 a.m.
Created at: April 29, 2026, 9:16 p.m.