Triple

T20003134
Position Surface form Disambiguated ID Type / Status
Subject macOS High Sierra E494384 entity
Predicate includesApplication P14571 FINISHED
Object Calendar 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: Calendar | Statement: [macOS High Sierra, includesApplication, Calendar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Calendar
Context triple: [macOS High Sierra, includesApplication, Calendar]
  • A. Calendar
    Calendar is a 2003 Canadian drama film directed by Atom Egoyan, known for its introspective narrative and collaboration with cinematographer Paul Sarossy.
  • B. Calendar chosen
    Calendar is Apple's built-in calendar and scheduling application for macOS and iOS that lets users manage events, reminders, and time-based tasks.
  • C. Calendar Man
    Calendar Man is a DC Comics supervillain and recurring Batman adversary known for committing crimes themed around holidays and calendar dates.
  • D. Calendarium
    Calendarium is an influential 15th-century astronomical and calendrical work by the German mathematician and astronomer Regiomontanus, used for improving the accuracy of calendars and predicting celestial events.
  • E. Google Calendar
    Google Calendar is a time-management and scheduling service by Google that lets users create, share, and manage events and reminders across devices.
  • 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_69da626b2d748190886981ea90c8b2ea completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e661a2e34481908a495cc5d077c41f completed April 20, 2026, 5:25 p.m.
Created at: April 11, 2026, 3:33 p.m.