Triple

T21812640
Position Surface form Disambiguated ID Type / Status
Subject Plurilateral Agreement on Government Procurement E538515 entity
Predicate shortName P43 FINISHED
Object GPA
The GPA is a World Trade Organization plurilateral agreement that sets rules to ensure open, fair, and transparent competition in government procurement among its parties.
 E1501740 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: GPA | Statement: [Plurilateral Agreement on Government Procurement, shortName, GPA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: GPA
Context triple: [Plurilateral Agreement on Government Procurement, shortName, GPA]
  • A. GPA
    GPA is an autoimmune form of vasculitis that causes inflammation of small- and medium-sized blood vessels, particularly affecting the respiratory tract and kidneys.
  • B. GPA
    GPA is an encryption and key management tool for GnuPG that provides a graphical interface for handling keys and securing data.
  • C. GPA
    GPA is the IATA airport code for Araxos Airport, a regional airport in western Greece serving the Patras area.
  • D. GPA
    GPA is a major Austrian trade union representing employees in commerce, banking, and related service sectors.
  • E. IGPA
    IGPA is a major Chilean stock market index that tracks the performance of a broad range of companies listed on the Santiago Stock Exchange.
  • 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: GPA
Triple: [Plurilateral Agreement on Government Procurement, shortName, GPA]
Generated description
The GPA is a World Trade Organization plurilateral agreement that sets rules to ensure open, fair, and transparent competition in government procurement among its parties.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: GPA
Target entity description: The GPA is a World Trade Organization plurilateral agreement that sets rules to ensure open, fair, and transparent competition in government procurement among its parties.
  • A. GPA
    GPA is an autoimmune form of vasculitis that causes inflammation of small- and medium-sized blood vessels, particularly affecting the respiratory tract and kidneys.
  • B. GPA
    GPA is an encryption and key management tool for GnuPG that provides a graphical interface for handling keys and securing data.
  • C. GPA
    GPA is the IATA airport code for Araxos Airport, a regional airport in western Greece serving the Patras area.
  • D. GPA
    GPA is a major Austrian trade union representing employees in commerce, banking, and related service sectors.
  • E. IGPA
    IGPA is a major Chilean stock market index that tracks the performance of a broad range of companies listed on the Santiago Stock Exchange.
  • 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_69e0c473f0f8819086c9d1b4a143bd67 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69f07cc7ec1c8190a5420b44a49ae32f completed April 28, 2026, 9:24 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0a3e8ab4e0819088cba8246a57f512 completed May 17, 2026, 10:17 p.m.
NEDg Description generation batch_6a0a3f21b83c81908353647d34b2d280 completed May 17, 2026, 10:20 p.m.
NED2 Entity disambiguation (via description) batch_6a0a3fcce3a48190ac13842ad0a9dfba completed May 17, 2026, 10:23 p.m.
Created at: April 16, 2026, 6:53 p.m.