Triple

T11419062
Position Surface form Disambiguated ID Type / Status
Subject WPP plc E270569 entity
Predicate hasSubsidiary P254 FINISHED
Object BCW
BCW is a global communications and public relations agency known for providing integrated marketing, branding, and strategic communications services to clients worldwide.
 E924420 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: BCW | Statement: [WPP plc, hasSubsidiary, BCW]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: BCW
Context triple: [WPP plc, hasSubsidiary, BCW]
  • A. WBLA
    WBLA is the commonly used abbreviation for the West Bengal Legislative Assembly, the unicameral state legislature of West Bengal, India.
  • B. CUWBC
    CUWBC is the rowing club that represents the women of the University of Cambridge in major intercollegiate boat races, including the historic Boat Race against Oxford.
  • C. CWF
    CWF is the station code for Canary Wharf DLR station, a key stop on London's Docklands Light Railway serving the Canary Wharf business district.
  • D. BPW
    BPW is the National Rail station code for Bristol Parkway railway station, a major rail hub serving the northern suburbs of Bristol, England.
  • E. WWA
    WWA is the National Rail station code for Woolwich Arsenal railway station in southeast London.
  • 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: BCW
Triple: [WPP plc, hasSubsidiary, BCW]
Generated description
BCW is a global communications and public relations agency known for providing integrated marketing, branding, and strategic communications services to clients worldwide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: BCW
Target entity description: BCW is a global communications and public relations agency known for providing integrated marketing, branding, and strategic communications services to clients worldwide.
  • A. WBLA
    WBLA is the commonly used abbreviation for the West Bengal Legislative Assembly, the unicameral state legislature of West Bengal, India.
  • B. CUWBC
    CUWBC is the rowing club that represents the women of the University of Cambridge in major intercollegiate boat races, including the historic Boat Race against Oxford.
  • C. CWF
    CWF is the station code for Canary Wharf DLR station, a key stop on London's Docklands Light Railway serving the Canary Wharf business district.
  • D. BPW
    BPW is the National Rail station code for Bristol Parkway railway station, a major rail hub serving the northern suburbs of Bristol, England.
  • E. WWA
    WWA is the National Rail station code for Woolwich Arsenal railway station in southeast London.
  • 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_69d6aaddeaa8819088b30ef7b50598c9 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d801b20ce08190befc98379b879985 completed April 9, 2026, 7:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69e5b88f80d88190b91b63d0b7457c25 completed April 20, 2026, 5:24 a.m.
NEDg Description generation batch_69e5c28d3824819097ff84cb4e13c923 completed April 20, 2026, 6:07 a.m.
NED2 Entity disambiguation (via description) batch_69e5c451c6c88190bcbb1f54ede35d29 completed April 20, 2026, 6:14 a.m.
Created at: April 8, 2026, 9:34 p.m.