Triple

T21038489
Position Surface form Disambiguated ID Type / Status
Subject Kings Dominion E518254 entity
Predicate hostsEvent P613 FINISHED
Object Halloween Haunt 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: Halloween Haunt | Statement: [Kings Dominion, hostsEvent, Halloween Haunt]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Halloween Haunt
Context triple: [Kings Dominion, hostsEvent, Halloween Haunt]
  • A. Halloween Haunt
    Halloween Haunt is a large-scale, horror-themed nighttime event at Canada's Wonderland featuring haunted mazes, scare zones, live entertainment, and seasonal attractions during the Halloween season.
  • B. Halloween Haunt chosen
    Halloween Haunt is a seasonal Halloween-themed nighttime event at California’s Great America featuring haunted mazes, scare zones, live entertainment, and special attractions.
  • C. Halloween City
    Halloween City is a seasonal retail chain specializing in Halloween costumes, decorations, and party supplies.
  • D. 31 Nights of Halloween
    31 Nights of Halloween is Freeform’s annual month-long programming event featuring Halloween-themed movies, specials, and family-friendly spooky content.
  • E. Howl-O-Scream
    Howl-O-Scream is a large-scale Halloween-themed event featuring haunted houses, scare zones, and live entertainment held annually at Busch Gardens Williamsburg and other SeaWorld Parks & Entertainment locations.
  • 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_69e0b50438e08190917e2538bb8bc034 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e6fcee13b08190a8b3372f6759cd1b completed April 21, 2026, 4:28 a.m.
Created at: April 16, 2026, 2:12 p.m.