Triple

T1097406
Position Surface form Disambiguated ID Type / Status
Subject Social Security Disability Insurance E24299 entity
Predicate benefitTaxStatus P24100 FINISHED
Object benefits may be taxable depending on income 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: benefits may be taxable depending on income | Statement: [Social Security Disability Insurance, benefitTaxStatus, benefits may be taxable depending on income]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: benefitTaxStatus
Context triple: [Social Security Disability Insurance, benefitTaxStatus, benefits may be taxable depending on income]
  • A. taxpayerBenefitForm
    Indicates that there is a specific form documenting or enabling a benefit granted to a taxpayer.
  • B. hasBenefit
    Indicates that one entity provides an advantage, improvement, or positive outcome to another entity.
  • C. taxType
    Indicates the specific category or classification of tax that applies to an entity, transaction, or amount.
  • D. typeOfTaxpayerCovered
    Indicates the category or kind of taxpayer to which a particular rule, obligation, or provision applies.
  • E. benefitForm
    Indicates that one entity is a specific form, type, or variant in which a benefit is provided or realized for another entity.
  • 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_69a4940542308190ac2a0b1f730b7cfc completed March 1, 2026, 7:31 p.m.
NER Named-entity recognition batch_69a4b9a1d3108190b2a304fef429848d completed March 1, 2026, 10:11 p.m.
PD Predicate disambiguation batch_69a4b745ef3481909a7ce4647c8567b3 completed March 1, 2026, 10:01 p.m.
PDg Predicate description generation batch_69a4b8f1097881908932d7eea4331917 completed March 1, 2026, 10:08 p.m.
Created at: March 1, 2026, 7:42 p.m.