Triple

T1920982
Position Surface form Disambiguated ID Type / Status
Subject Letter to You E40123 entity
Predicate hasTrack P3284 FINISHED
Object Ghosts E136035 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: Ghosts | Statement: [Letter to You, hasTrack, Ghosts]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ghosts
Context triple: [Letter to You, hasTrack, Ghosts]
  • A. Ghosts chosen
    "Ghosts" is a song featured on the album "Carry On," known for its evocative themes and atmospheric sound.
  • B. GHOST!
    GHOST! is a track by Kid Cudi from his album "Man on the Moon II: The Legend of Mr. Rager," known for its introspective lyrics and atmospheric production.
  • C. The Ghost
    The Ghost is the spectral apparition of Hamlet’s deceased father in Shakespeare’s tragedy, whose revelations set the play’s revenge plot in motion.
  • D. Beautiful Ghosts
    "Beautiful Ghosts" is an original song co-written by Taylor Swift and Andrew Lloyd Webber for the 2019 film adaptation of the musical Cats.
  • E. Ghost
    Ghost is a 1990 romantic fantasy thriller film best known for its blend of supernatural drama and romance, starring Patrick Swayze, Demi Moore, and Whoopi Goldberg in an Oscar-winning role.
  • 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_69a8864298748190a2f2fd34f7ef8d77 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69abb231de14819091da3a20ed03c430 completed March 7, 2026, 5:05 a.m.
NED1 Entity disambiguation (via context triple) batch_69adf3e192288190873b58b98ce928e8 completed March 8, 2026, 10:10 p.m.
Created at: March 4, 2026, 7:35 p.m.