Triple

T17557778
Position Surface form Disambiguated ID Type / Status
Subject Lightning Web Components E427629 entity
Predicate runsOn P23 FINISHED
Object Salesforce Mobile App NE NERFINISHED

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: Salesforce Mobile App | Statement: [Lightning Web Components, runsOn, Salesforce Mobile App]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Salesforce Mobile App
Context triple: [Lightning Web Components, runsOn, Salesforce Mobile App]
  • A. Salesforce chosen
    Salesforce is a leading cloud-based customer relationship management (CRM) company known for its suite of enterprise applications for sales, service, marketing, and analytics.
  • B. SDFC
    SDFC is the commonly used abbreviation for San Diego FC, a professional soccer club based in San Diego, California.
  • C. AppExchange
    AppExchange is Salesforce’s online marketplace for third-party business applications and integrations built on or for the Salesforce platform.
  • D. Zoho CRM
    Zoho CRM is a cloud-based customer relationship management platform designed to help businesses manage sales, marketing, and customer support in a unified system.
  • E. Adobe Mobile Services
    Adobe Mobile Services is a suite of tools within Adobe’s marketing platform that helps businesses measure, analyze, and optimize user engagement and campaigns across mobile apps.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d889df6dc081908f67dbadc03c07ee completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e4562413d08190acaa5272046d3626 completed April 19, 2026, 4:12 a.m.
Created at: April 10, 2026, 5:50 a.m.