Triple

T18844820
Position Surface form Disambiguated ID Type / Status
Subject Companies Act, 2013 E460888 entity
Predicate establishes P986 FINISHED
Object Serious Fraud Investigation Office NE NERFINISHED

How this triple was built (3 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: Serious Fraud Investigation Office | Statement: [Companies Act, 2013, establishes, Serious Fraud Investigation Office]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Serious Fraud Investigation Office
Context triple: [Companies Act, 2013, establishes, Serious Fraud Investigation Office]
  • A. Serious Fraud Office
    The Serious Fraud Office is a UK government agency responsible for investigating and prosecuting serious or complex fraud, bribery, and corruption cases.
  • B. Serious Fraud Office (New Zealand)
    The Serious Fraud Office (New Zealand) is a specialist government agency responsible for investigating and prosecuting serious or complex financial crime and corruption in New Zealand.
  • C. Economic Crime Directorate
    The Economic Crime Directorate is a specialist unit of the City of London Police responsible for investigating and combating complex financial and economic crimes in the UK’s financial center.
  • D. European Anti-Fraud Office
    The European Anti-Fraud Office (OLAF) is an EU body responsible for investigating fraud, corruption, and other illegal activities affecting the European Union’s financial interests.
  • E. Anti-Corruption Foundation
    The Anti-Corruption Foundation is a Russian non-profit organization known for investigating and exposing high-level government corruption and promoting political transparency.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Serious Fraud Investigation Office
Target entity description: The Serious Fraud Investigation Office is a specialized Indian government agency that investigates complex corporate frauds and financial irregularities.
  • A. Serious Fraud Office
    The Serious Fraud Office is a UK government agency responsible for investigating and prosecuting serious or complex fraud, bribery, and corruption cases.
  • B. Serious Fraud Office (New Zealand)
    The Serious Fraud Office (New Zealand) is a specialist government agency responsible for investigating and prosecuting serious or complex financial crime and corruption in New Zealand.
  • C. Economic Crime Directorate
    The Economic Crime Directorate is a specialist unit of the City of London Police responsible for investigating and combating complex financial and economic crimes in the UK’s financial center.
  • D. European Anti-Fraud Office
    The European Anti-Fraud Office (OLAF) is an EU body responsible for investigating fraud, corruption, and other illegal activities affecting the European Union’s financial interests.
  • E. Anti-Corruption Foundation
    The Anti-Corruption Foundation is a Russian non-profit organization known for investigating and exposing high-level government corruption and promoting political transparency.
  • F. None of above. chosen

Provenance (2 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_69d8dcfa11e4819090ab1ef5bdcd2b2e completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5b8ed944c81908592f0c34e5727a0 completed April 20, 2026, 5:26 a.m.
Created at: April 10, 2026, 11:56 a.m.