Triple

T16215381
Position Surface form Disambiguated ID Type / Status
Subject Mary Beth Hurt E393579 entity
Predicate notableWork P4 FINISHED
Object Light Sleeper E563176 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: Light Sleeper | Statement: [Mary Beth Hurt, notableWork, Light Sleeper]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Light Sleeper
Context triple: [Mary Beth Hurt, notableWork, Light Sleeper]
  • A. Light Sleeper chosen
    Light Sleeper is a 1992 neo-noir drama film written and directed by Paul Schrader, following a drug courier in New York City undergoing a moral and existential crisis.
  • B. O Sono
    O Sono is a painting by Brazilian modernist artist Tarsila do Amaral, exemplifying her distinctive style that blends avant-garde techniques with themes from Brazilian culture.
  • C. Sleeper
    "Sleeper" is a 2013 acoustic-leaning studio album by American garage rock musician Ty Segall, noted for its introspective and emotionally raw songwriting.
  • D. Sleeper
    Sleeper is a British Britpop band best known for their mid-1990s success with hook-driven guitar pop and prominent presence on the UK indie and alternative charts.
  • E. Sleeper
    Sleeper is a 1973 science-fiction comedy film by Woody Allen that satirizes futuristic society through the misadventures of a man who wakes up 200 years after being cryogenically frozen.
  • 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_69d87f1f5bd08190bd01cac0d5b9d2ef completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e227f4685c8190aa1e9304e4a62d13 completed April 17, 2026, 12:30 p.m.
NED1 Entity disambiguation (via context triple) batch_6a000794e6c881909c4521e4dd031971 completed May 10, 2026, 4:20 a.m.
Created at: April 10, 2026, 5:03 a.m.