Triple

T13881483
Position Surface form Disambiguated ID Type / Status
Subject John Van Druten E333727 entity
Predicate notableWork P4 FINISHED
Object Leave Her to Heaven E395660 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: Leave Her to Heaven | Statement: [John Van Druten, notableWork, Leave Her to Heaven]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Leave Her to Heaven
Context triple: [John Van Druten, notableWork, Leave Her to Heaven]
  • A. Leave Her to Heaven chosen
    Leave Her to Heaven is a 1945 Technicolor film noir melodrama starring Gene Tierney, renowned for its lush visuals and psychologically intense story of obsessive love.
  • B. For Heaven's Sake
    For Heaven's Sake is a 1926 silent romantic comedy film starring Harold Lloyd as a wealthy man who becomes involved with a mission worker in the city's slums.
  • C. No Place in Heaven
    No Place in Heaven is a 2015 pop album by British-Lebanese singer-songwriter Mika that blends theatrical melodies with introspective, personal lyrics.
  • D. Heaven Knows
    "Heaven Knows" is a 1985 soulful pop single by British singer Jaki Graham that became one of her signature hits in the mid-1980s.
  • E. Heaven Knows
    "Heaven Knows" is a song featured on Lenny Kravitz's album *Blue Electric Light*.
  • 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_69d81c5dd2d48190b7a5fc1e009de936 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de0be8566881908b8902e3cd567669 completed April 14, 2026, 9:42 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7c711f9b08190aa5981320597e83b completed May 3, 2026, 10:07 p.m.
Created at: April 9, 2026, 10:15 p.m.