Triple

T10296062
Position Surface form Disambiguated ID Type / Status
Subject David Duffield E241490 entity
Predicate founded P104 FINISHED
Object Workday, Inc. E387789 NE FINISHED

How this triple was built (2 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: Workday, Inc. | Statement: [David Duffield, founded, Workday, Inc.]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Workday, Inc.
Context triple: [David Duffield, founded, Workday, Inc.]
  • A. Workday chosen
    Workday is a cloud-based enterprise software company best known for its human capital management and financial management applications used by large organizations worldwide.
  • B. Paycor, Inc.
    Paycor, Inc. is a U.S.-based provider of human capital management and payroll software solutions for small and midsize businesses.
  • C. Zenefits
    Zenefits is a cloud-based human resources and benefits administration platform that helps small and mid-sized businesses manage payroll, benefits, compliance, and HR processes in one system.
  • D. Groupe ADP
    Groupe ADP is a major French airport management company that owns and operates the Paris-area airports and provides aviation and related services worldwide.
  • E. Recruit Holdings
    Recruit Holdings is a Japanese human resources and marketing conglomerate best known globally as the owner of major job search platform Indeed.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d381aaafc08190af475ef58dc16aba completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4d2ea9b3c8190b11518b259d5825c completed April 7, 2026, 9:48 a.m.
NED1 Entity disambiguation (via context triple) batch_69d794d34978819083ce709fa2dcaca7 completed April 9, 2026, noon
Created at: April 6, 2026, 11:43 a.m.