Triple

T18173008
Position Surface form Disambiguated ID Type / Status
Subject Plaxo E435077 entity
Predicate dataFormat P130 FINISHED
Object vCard 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: vCard | Statement: [Plaxo, dataFormat, vCard]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: vCard
Context triple: [Plaxo, dataFormat, vCard]
  • A. vCard chosen
    vCard is a standardized file format for electronic business cards that stores and exchanges contact information such as names, phone numbers, addresses, and email details across different applications and devices.
  • B. Cardfile
    Cardfile is a simple card-based personal information manager included with early versions of Microsoft Windows for storing and organizing small text notes.
  • C. vCalendar
    vCalendar is an early electronic calendaring and scheduling format that served as a predecessor to the more widely adopted iCalendar standard.
  • D. CardDAV
    CardDAV is an open standard protocol that enables remote access, synchronization, and management of contact data over the Web using HTTP and WebDAV.
  • E. Kontact personal information manager
    Kontact personal information manager is an integrated suite of KDE applications for handling email, calendars, contacts, tasks, and other personal information on the desktop.
  • 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_69d8b90b7a188190b3fc7b8d4a6cd20a completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4df56d0a88190af3f407d2a3bb74f completed April 19, 2026, 1:57 p.m.
Created at: April 10, 2026, 10:30 a.m.