Triple

T18173012
Position Surface form Disambiguated ID Type / Status
Subject Plaxo E435077 entity
Predicate competitor P1375 FINISHED
Object Yahoo! Address Book 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: Yahoo! Address Book | Statement: [Plaxo, competitor, Yahoo! Address Book]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yahoo! Address Book
Context triple: [Plaxo, competitor, Yahoo! Address Book]
  • A. Yahoo chosen
    Yahoo is a pioneering web services company best known for its web portal, search engine, email service, and online media offerings.
  • B. Naver Contacts
    Naver Contacts is Naver’s cloud-based address book service that manages and syncs users’ contact information across Naver’s apps and devices.
  • C. The Address Book
    The Address Book is a conceptual art project and book by French artist Sophie Calle in which she investigates the life of a stranger solely through the contacts listed in his lost address book, exploring themes of privacy, voyeurism, and identity.
  • D. Google Contacts
    Google Contacts is a contact management service by Google that stores and syncs users’ personal and professional contact information across Google’s apps and devices.
  • E. Windows Address Book
    Windows Address Book is a built-in Windows component that stores and manages contact information for use by email and messaging applications.
  • 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.