Triple

T34983574
Position Surface form Disambiguated ID Type / Status
Subject Work Capability Assessment E1008880 entity
Predicate previousProvider P25617 FINISHED
Object Atos Healthcare
Atos Healthcare was a private company contracted by the UK government to conduct controversial disability and work capability assessments for welfare claimants.
 E2119777 NE FINISHED

How this triple was built (3 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: Atos Healthcare | Statement: [Work Capability Assessment, previousProvider, Atos Healthcare]
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: Atos Healthcare
Triple: [Work Capability Assessment, previousProvider, Atos Healthcare]
Generated description
Atos Healthcare was a private company contracted by the UK government to conduct controversial disability and work capability assessments for welfare claimants.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: previousProvider
Context triple: [Work Capability Assessment, previousProvider, Atos Healthcare]
  • A. previousSupplier
    Indicates that one entity served as the supplier of another entity at an earlier time but no longer holds that role.
  • B. previousServiceType
    Indicates that one service type directly preceded another in a sequence or history of services.
  • C. previousComponent
    Indicates that one component directly precedes another in an ordered sequence or structure.
  • D. previousMaintainer chosen
    Indicates that one entity formerly held responsibility for maintaining another entity before the current maintainer.
  • E. previousRepository
    Indicates that one repository directly precedes another in a version, history, or sequence of repositories.
  • F. None of above.

Provenance (6 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_69f76dc844a48190881951fffb83d17e completed May 3, 2026, 3:46 p.m.
NER Named-entity recognition batch_69ff53389a0481908b2baeb43c6294f0 completed May 9, 2026, 3:31 p.m.
NED1 Entity disambiguation (via context triple) batch_6a37b28222a4819083274fb2c3e40f8e completed June 21, 2026, 9:44 a.m.
NEDg Description generation batch_6a37b30dbce8819090cd5023e0bb4279 completed June 21, 2026, 9:46 a.m.
NED2 Entity disambiguation (via description) batch_6a37b3e4e4e48190a694902881b3a08f completed June 21, 2026, 9:50 a.m.
PD Predicate disambiguation batch_69ff52e2b4b88190b38d160d771fe14b completed May 9, 2026, 3:29 p.m.
Created at: May 3, 2026, 4:01 p.m.