Triple

T18453456
Position Surface form Disambiguated ID Type / Status
Subject Haymarket Media Group E450843 entity
Predicate notableWork P4 FINISHED
Object GPonline
GPonline is a UK-based digital news and information platform providing clinical, professional, and policy content for general practitioners and primary care professionals.
 E1325867 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: GPonline | Statement: [Haymarket Media Group, notableWork, GPonline]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: GPonline
Context triple: [Haymarket Media Group, notableWork, GPonline]
  • A. GPC
    GPC is a discount cigarette brand produced by the tobacco company Brown & Williamson.
  • B. GPC
    GPC is the GNU Pascal Compiler, a free, open-source Pascal compiler that is part of the GNU Compiler Collection (GCC) project.
  • C. GPC
    GPC is the commonly used acronym for the Green Party of Canada, a federal political party focused on environmentalism and social justice.
  • D. GOV.UK Pay
    GOV.UK Pay is a UK government digital payments platform that enables public sector services to take secure online card and alternative payments from users.
  • E. Orange UK
    Orange UK was a major British mobile network operator that became part of EE following its merger with T-Mobile UK.
  • 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: GPonline
Triple: [Haymarket Media Group, notableWork, GPonline]
Generated description
GPonline is a UK-based digital news and information platform providing clinical, professional, and policy content for general practitioners and primary care professionals.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: GPonline
Target entity description: GPonline is a UK-based digital news and information platform providing clinical, professional, and policy content for general practitioners and primary care professionals.
  • A. GPC
    GPC is a discount cigarette brand produced by the tobacco company Brown & Williamson.
  • B. GPC
    GPC is the GNU Pascal Compiler, a free, open-source Pascal compiler that is part of the GNU Compiler Collection (GCC) project.
  • C. GPC
    GPC is the commonly used acronym for the Green Party of Canada, a federal political party focused on environmentalism and social justice.
  • D. GOV.UK Pay
    GOV.UK Pay is a UK government digital payments platform that enables public sector services to take secure online card and alternative payments from users.
  • E. Orange UK
    Orange UK was a major British mobile network operator that became part of EE following its merger with T-Mobile UK.
  • 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_69d8d38345688190b565eac2e4cd7935 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e5264a49ec8190aa43381d93a55e91 completed April 19, 2026, 7 p.m.
NED1 Entity disambiguation (via context triple) batch_6a040fe5eb1081909ecdf53f4b6b9370 completed May 13, 2026, 5:45 a.m.
NEDg Description generation batch_6a043a81cd58819089df50804870952e completed May 13, 2026, 8:46 a.m.
NED2 Entity disambiguation (via description) batch_6a043c0580048190afd9fe46e6863918 completed May 13, 2026, 8:53 a.m.
Created at: April 10, 2026, 11:31 a.m.