Triple

T38017676
Position Surface form Disambiguated ID Type / Status
Subject Housing Benefit (for most new working-age claimants) E948539 entity
Predicate reductionFactor P189860 FINISHED
Object non-dependant deductions 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: non-dependant deductions | Statement: [Housing Benefit (for most new working-age claimants), reductionFactor, non-dependant deductions]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: reductionFactor
Context triple: [Housing Benefit (for most new working-age claimants), reductionFactor, non-dependant deductions]
  • A. reduction
    Indicates a relationship where something is decreased in amount, size, intensity, or degree compared to a prior state or reference.
  • B. reductionTo
    Indicates that one entity is transformed, simplified, or mapped into another entity that is considered an equivalent or simpler form, often preserving essential properties.
  • C. reductionFrom
    Indicates that one entity is derived by simplifying, decreasing, or transforming another entity, typically resulting in a smaller, less complex, or less resource-intensive form.
  • D. reductionFrom
    Indicates that one entity is derived by simplifying, decreasing, or transforming another entity, typically resulting in a smaller, less complex, or less costly version.
  • E. reducedNumberOf
    Indicates that the subject has a smaller quantity or count of the specified object or attribute compared to a prior state or reference level.
  • 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_69f76efc10448190aff5fb566b98f952 completed May 3, 2026, 3:51 p.m.
NER Named-entity recognition batch_69fbca6c066c8190a1599202f341417f completed May 6, 2026, 11:10 p.m.
PD Predicate disambiguation batch_69fbc8ee04f08190977b7ad70fc85896 completed May 6, 2026, 11:04 p.m.
PDg Predicate description generation batch_69fbc993caa881908c16c3e21efaeef9 completed May 6, 2026, 11:07 p.m.
Created at: May 3, 2026, 4:20 p.m.