Triple

T1050374
Position Surface form Disambiguated ID Type / Status
Subject National Insurance contributions E22683 entity
Predicate basisOfLiability P20568 FINISHED
Object earnings 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: earnings | Statement: [National Insurance contributions, basisOfLiability, earnings]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: basisOfLiability
Context triple: [National Insurance contributions, basisOfLiability, earnings]
  • A. establishesLiabilityFor
    Indicates that one party is held legally responsible or accountable for a particular act, omission, or outcome.
  • B. legalBasis
    Indicates the legal rule, authority, or justification under which an action, decision, or status is established or carried out.
  • C. legalBasisWeakenedBy
    Indicates that the legal force, validity, or effectiveness of something is reduced or undermined by another factor, action, or decision.
  • D. claimsFoundationBy chosen
    Indicates that one entity asserts or declares that another entity serves as its basis, origin, or underlying foundation.
  • E. responsibleFor
    Indicates that one entity has a duty, obligation, or role to manage, oversee, or be accountable for another entity or outcome.
  • 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_69a493da02e081908c13ff5e02a0fe7a completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4b8b40d50819091cb37a2236e82ee completed March 1, 2026, 10:07 p.m.
PD Predicate disambiguation batch_69a4b7309cc481908ed839b0b8d75dbf completed March 1, 2026, 10:01 p.m.
Created at: March 1, 2026, 7:42 p.m.