Triple

T8071847
Position Surface form Disambiguated ID Type / Status
Subject New York City Employees’ Retirement System E188390 entity
Predicate memberContributionSource P30146 FINISHED
Object payroll deductions from members 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: payroll deductions from members | Statement: [New York City Employees’ Retirement System, memberContributionSource, payroll deductions from members]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: memberContributionSource
Context triple: [New York City Employees’ Retirement System, memberContributionSource, payroll deductions from members]
  • A. hasContributionFrom chosen
    Indicates that something (such as a work, project, or outcome) is created, influenced, or supported in part by a specified contributor.
  • B. tributeFrom
    Indicates that one entity pays or provides tribute, often as a sign of submission or obligation, to another entity.
  • C. tributeMethod
    Indicates the means or manner by which tribute is given, delivered, or fulfilled between parties.
  • D. tributeSystem
    Indicates a relationship where one entity regularly provides payments, goods, or services to another as a sign of submission, allegiance, or obligation.
  • E. memberRemuneration
    Indicates that a member receives payment or compensation, typically for their role, services, or participation within an organization or group.
  • 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_69ca82b50c708190863f661d438e68df completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb4046a2148190a584e33bcf53cf22 completed March 31, 2026, 3:32 a.m.
PD Predicate disambiguation batch_69cb049cd51c8190bb3b0f503e42fa8d completed March 30, 2026, 11:17 p.m.
Created at: March 30, 2026, 5:27 p.m.