Triple

T20137141
Position Surface form Disambiguated ID Type / Status
Subject The Unicorn E491052 entity
Predicate title P38 FINISHED
Object The Unicorn 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: The Unicorn | Statement: [The Unicorn, title, The Unicorn]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: The Unicorn
Context triple: [The Unicorn, title, The Unicorn]
  • A. The Unicorn
    "The Unicorn" is a whimsical folk song, popularized by The Irish Rovers, that humorously tells the story of how unicorns missed boarding Noah’s Ark.
  • B. The Unicorn
    The Unicorn is an American television sitcom that follows a widowed father navigating single parenthood and dating, known for its heartfelt humor and ensemble cast.
  • C. The Unicorn
    The Unicorn is an independent comedy film known for its offbeat exploration of modern relationships and commitment.
  • D. The White Unicorn
    The White Unicorn is a British film featuring actress Moira Lister in a prominent role.
  • E. The Black Unicorn
    The Black Unicorn is a fantasy novel by Terry Brooks in the Magic Kingdom of Landover series, following former lawyer-turned-king Ben Holiday as he confronts a mysterious and powerful unicorn tied to Landover’s fate.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide. chosen

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_69da62651a0c8190a3e05e95e056a66b completed April 11, 2026, 3:01 p.m.
NER Named-entity recognition batch_69e6676879f48190a59da04393d2a8cc completed April 20, 2026, 5:50 p.m.
Created at: April 11, 2026, 11:32 p.m.