Triple

T22636785
Position Surface form Disambiguated ID Type / Status
Subject Maryland State Retirement and Pension System E558701 entity
Predicate hasComponent P35 FINISHED
Object Maryland Correctional Officers Retirement System
The Maryland Correctional Officers Retirement System is a public pension program that provides retirement benefits specifically for eligible correctional officers employed by the state of Maryland.
E1550742 NE FINISHED

How this triple was built (4 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: Maryland Correctional Officers Retirement System | Statement: [Maryland State Retirement and Pension System, hasComponent, Maryland Correctional Officers Retirement System]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Maryland Correctional Officers Retirement System
Context triple: [Maryland State Retirement and Pension System, hasComponent, Maryland Correctional Officers Retirement System]
  • A. Maryland Law Enforcement Officers Pension System
    The Maryland Law Enforcement Officers Pension System is a public retirement program that provides pension benefits specifically for eligible law enforcement officers in the state of Maryland.
  • B. Maryland State Retirement and Pension System
    The Maryland State Retirement and Pension System is the public pension fund that manages retirement benefits and investment assets for Maryland’s state employees, teachers, and other eligible public workers.
  • C. Maryland Judges Retirement System
    The Maryland Judges Retirement System is a public pension program that provides retirement benefits to eligible judges serving in the state of Maryland.
  • D. Public Service Commission of Maryland
    The Public Service Commission of Maryland is the state regulatory agency responsible for overseeing and regulating public utilities and services, including electricity, gas, telecommunications, and transportation, within Maryland.
  • E. Maryland Correctional Enterprises
    Maryland Correctional Enterprises is a state-run prison industry program in Maryland that provides work and job training opportunities to incarcerated individuals through the production of goods and services for government and nonprofit customers.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Maryland Correctional Officers Retirement System
Triple: [Maryland State Retirement and Pension System, hasComponent, Maryland Correctional Officers Retirement System]
Generated description
The Maryland Correctional Officers Retirement System is a public pension program that provides retirement benefits specifically for eligible correctional officers employed by the state of Maryland.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Maryland Correctional Officers Retirement System
Target entity description: The Maryland Correctional Officers Retirement System is a public pension program that provides retirement benefits specifically for eligible correctional officers employed by the state of Maryland.
  • A. Maryland Law Enforcement Officers Pension System
    The Maryland Law Enforcement Officers Pension System is a public retirement program that provides pension benefits specifically for eligible law enforcement officers in the state of Maryland.
  • B. Maryland State Retirement and Pension System
    The Maryland State Retirement and Pension System is the public pension fund that manages retirement benefits and investment assets for Maryland’s state employees, teachers, and other eligible public workers.
  • C. Maryland Judges Retirement System
    The Maryland Judges Retirement System is a public pension program that provides retirement benefits to eligible judges serving in the state of Maryland.
  • D. Public Service Commission of Maryland
    The Public Service Commission of Maryland is the state regulatory agency responsible for overseeing and regulating public utilities and services, including electricity, gas, telecommunications, and transportation, within Maryland.
  • E. Maryland Correctional Enterprises
    Maryland Correctional Enterprises is a state-run prison industry program in Maryland that provides work and job training opportunities to incarcerated individuals through the production of goods and services for government and nonprofit customers.
  • F. None of above. chosen

Provenance (5 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_69e245467d9881908d6985bd0db7a1f1 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f1700e11688190b33e280a653db141 completed April 29, 2026, 2:42 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b7ec21604819081a4627e8e8d43f5 completed May 18, 2026, 9:04 p.m.
NEDg Description generation batch_6a0b80ed9e988190adbb4dd1c8f94513 completed May 18, 2026, 9:13 p.m.
NED2 Entity disambiguation (via description) batch_6a0b84a11100819081703dd288cb401f completed May 18, 2026, 9:29 p.m.
Created at: April 17, 2026, 3:03 p.m.