Triple

T13899602
Position Surface form Disambiguated ID Type / Status
Subject Queensland Police Service E334183 entity
Predicate hasAbbreviation P43 FINISHED
Object QPS
QPS is the primary law enforcement agency responsible for policing and public safety across the Australian state of Queensland.
 E1068348 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: QPS | Statement: [Queensland Police Service, hasAbbreviation, QPS]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: QPS
Context triple: [Queensland Police Service, hasAbbreviation, QPS]
  • A. OAQPS
    OAQPS is a division of the U.S. Environmental Protection Agency responsible for developing national programs, policies, and regulations to control air pollution and protect air quality.
  • B. Qos
    Qos is the chief national god of the ancient Edomites, often linked to storm and warrior attributes in the religious traditions of the Levant.
  • C. QPP
    QPP is a public pension program in Quebec that provides retirement, disability, and survivor benefits to eligible workers and their families.
  • D. Q’s
    Q’s is the nickname commonly used for the former American Basketball Association team the San Diego Conquistadors.
  • E. MQI
    MQI (Message Queue Interface) is a programming API used to send and receive messages via IBM MQ message queuing systems.
  • 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: QPS
Triple: [Queensland Police Service, hasAbbreviation, QPS]
Generated description
QPS is the primary law enforcement agency responsible for policing and public safety across the Australian state of Queensland.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: QPS
Target entity description: QPS is the primary law enforcement agency responsible for policing and public safety across the Australian state of Queensland.
  • A. OAQPS
    OAQPS is a division of the U.S. Environmental Protection Agency responsible for developing national programs, policies, and regulations to control air pollution and protect air quality.
  • B. Qos
    Qos is the chief national god of the ancient Edomites, often linked to storm and warrior attributes in the religious traditions of the Levant.
  • C. QPP
    QPP is a public pension program in Quebec that provides retirement, disability, and survivor benefits to eligible workers and their families.
  • D. Q’s
    Q’s is the nickname commonly used for the former American Basketball Association team the San Diego Conquistadors.
  • E. MQI
    MQI (Message Queue Interface) is a programming API used to send and receive messages via IBM MQ message queuing systems.
  • 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_69d81c5eaa9c819083b1ff8689179565 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de25d8897881908b770cdb565898d4 completed April 14, 2026, 11:32 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7c720b4988190aee1f1f09877212d completed May 3, 2026, 10:07 p.m.
NEDg Description generation batch_69f7c86a3640819081ed689bd271f909 completed May 3, 2026, 10:12 p.m.
NED2 Entity disambiguation (via description) batch_69f7c9b2930c8190983f2c55a0dd35f6 completed May 3, 2026, 10:18 p.m.
Created at: April 9, 2026, 10:15 p.m.