Triple

T22395502
Position Surface form Disambiguated ID Type / Status
Subject Ouija E553618 entity
Predicate basedOn P98 FINISHED
Object Ouija board 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: Ouija board | Statement: [Ouija, basedOn, Ouija board]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ouija board
Context triple: [Ouija, basedOn, Ouija board]
  • A. Ouija Board
    Ouija Board is a celebrated British Thoroughbred racehorse and broodmare, best known for her multiple Group 1 victories including two Breeders’ Cup Filly & Mare Turf wins and an Epsom Oaks triumph.
  • B. Mr. Ouija
    "Mr. Ouija" is a dark, atmospheric hip-hop track by Bone Thugs-N-Harmony that showcases their rapid-fire flows and occult-themed lyrics.
  • C. Voodoo Doll
    A Voodoo Doll is a small human-shaped figure used in various folk magic and spiritual traditions, often believed to influence a person symbolically connected to it.
  • D. Ouija chosen
    Ouija is a 2014 supernatural horror film centered on a group of friends who unwittingly unleash a malevolent spirit after using a Ouija board.
  • E. Cootie
    Cootie is the nickname of Charles "Cootie" Williams, a prominent American jazz trumpeter known for his work with Duke Ellington and his distinctive growling plunger-muted style.
  • 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_69e11e4cf87c8190a1ff474daec326b7 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f1585e84b081908c95ed3e0d987ed8 completed April 29, 2026, 1:01 a.m.
Created at: April 16, 2026, 8:45 p.m.