Triple

T20317064
Position Surface form Disambiguated ID Type / Status
Subject State Second Pension E510405 entity
Predicate similarSchemeIn P139639 FINISHED
Object Northern Ireland additional state pension system 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: Northern Ireland additional state pension system | Statement: [State Second Pension, similarSchemeIn, Northern Ireland additional state pension system]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: similarSchemeIn
Context triple: [State Second Pension, similarSchemeIn, Northern Ireland additional state pension system]
  • A. moreSimilarTo
    Indicates that one entity bears a greater degree of similarity to a second entity than to a third entity, according to some defined similarity measure.
  • B. similarSeries
    Indicates that two series share notable similarities in content, style, or characteristics.
  • C. similarItemGroup
    Indicates that two or more items belong to the same group because they share similar characteristics, attributes, or functions.
  • D. lessSimilarTo
    Indicates that one entity is considered to share fewer similarities or a weaker resemblance with another entity compared to some reference or alternative.
  • E. similarCredentialAs
    Indicates that one credential is considered equivalent or closely matching another in terms of content, level, or recognition.
  • F. None of above. chosen

Provenance (4 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_69e0b4c7491c8190961113c4283b10b0 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e67788ca3c8190a3496fd54a5870d6 completed April 20, 2026, 6:59 p.m.
PD Predicate disambiguation batch_69e55b21b09081909e46691b6f45a07f completed April 19, 2026, 10:45 p.m.
PDg Predicate description generation batch_69e56702ad04819099c1c08f28d16809 completed April 19, 2026, 11:36 p.m.
Created at: April 16, 2026, 11:19 a.m.