Triple

T14003012
Position Surface form Disambiguated ID Type / Status
Subject Allstate Arena E336876 entity
Predicate hostedEvent P613 FINISHED
Object Disney on Ice E557046 NE FINISHED

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: Disney on Ice | Statement: [Allstate Arena, hostedEvent, Disney on Ice]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Disney on Ice
Context triple: [Allstate Arena, hostedEvent, Disney on Ice]
  • A. Disney on Ice chosen
    Disney on Ice is a touring ice-skating show produced by Feld Entertainment under license from Disney, featuring figure skaters performing stories and characters from Disney films.
  • B. Holidays on Ice
    "Holidays on Ice" is a collection of humorous and often darkly satirical holiday-themed essays by American writer David Sedaris.
  • C. Stars on Ice
    Stars on Ice is a long-running professional figure skating touring show featuring world-class skaters performing choreographed exhibitions across various cities.
  • D. Belles on Ice
    Belles on Ice is a segment from the animated holiday film "Mickey's Twice Upon a Christmas" featuring Disney characters in a festive ice-skating story.
  • E. Fantasmic!
    Fantasmic! is a nighttime multimedia spectacular at Disney parks that combines live performers, water projections, pyrotechnics, and Disney characters in a dramatic battle between good and evil.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d81c645c5c8190b1fd16a285a1b78a completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2ed06a50819093ddc64f55050689 completed April 14, 2026, 12:10 p.m.
NED1 Entity disambiguation (via context triple) batch_69fbaca180988190bbfc93bd708688d6 completed May 6, 2026, 9:03 p.m.
Created at: April 9, 2026, 10:19 p.m.