Triple

T6085671
Position Surface form Disambiguated ID Type / Status
Subject Treasurer of the Ordnance E135632 entity
Predicate usedAccountingSystem P37856 FINISHED
Object double-entry bookkeeping 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: double-entry bookkeeping | Statement: [Treasurer of the Ordnance, usedAccountingSystem, double-entry bookkeeping]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: usedAccountingSystem
Context triple: [Treasurer of the Ordnance, usedAccountingSystem, double-entry bookkeeping]
  • A. usedAccountingFirm
    Indicates that one entity engaged the professional services of a particular accounting firm.
  • B. usedAsAccountingUnitAfterReform
    Indicates that something served as an accounting unit following a specified reform.
  • C. usesBusinessSystem chosen
    Indicates that one entity makes use of a particular business system to perform its operations, processes, or functions.
  • D. accrualMethod
    Indicates the method or basis by which something (such as interest, revenue, or benefits) is accumulated or recognized over time.
  • E. usesCaseSystem
    Indicates that one entity employs or operates using a particular case system (e.g., grammatical or structural case-marking system).
  • 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_69c0087bcc788190b20f093d3a6c60ec completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c057891dc88190997c4e32b2261fb3 completed March 22, 2026, 8:56 p.m.
PD Predicate disambiguation batch_69c049f3b1ec8190bea67a7bec6442a5 completed March 22, 2026, 7:58 p.m.
Created at: March 22, 2026, 4:12 p.m.