Triple

T22768426
Position Surface form Disambiguated ID Type / Status
Subject Tattoo (2002 film) E563187 entity
Predicate title P38 FINISHED
Object Tattoo 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: Tattoo | Statement: [Tattoo (2002 film), title, Tattoo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tattoo
Context triple: [Tattoo (2002 film), title, Tattoo]
  • A. Tattoo
    "Tattoo" is a popular Afrobeats song by Nigerian singer Fireboy DML, known for its smooth, romantic vibe and melodic production.
  • B. Tattoo chosen
    "Tattoo" is a 2002 German crime thriller film directed by Robert Schwentke, centered on a dark investigation involving a serial killer and tattooed skin.
  • C. Tattoo
    Tattoo is the diminutive, sharply dressed assistant and sidekick on the television series "Fantasy Island," known for his iconic cry of "The plane! The plane!"
  • D. Tattoo
    "Tattoo" is a mid-2000s pop-R&B single by American singer Jordin Sparks that became one of her breakout hits following her American Idol win.
  • E. Tattoo
    "Tattoo" is a song by the English rock band The Who, featured on their 1967 concept album *The Who Sell Out*.
  • 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_69e24552e11c81909c2d61578a558bd7 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17b59c9cc8190a6edd68f3209a672 completed April 29, 2026, 3:30 a.m.
Created at: April 17, 2026, 3:27 p.m.