Triple

T4724419
Position Surface form Disambiguated ID Type / Status
Subject Ellen Kuras E104845 entity
Predicate workedOn P3 FINISHED
Object Summer of Sam E464759 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: Summer of Sam | Statement: [Ellen Kuras, workedOn, Summer of Sam]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Summer of Sam
Context triple: [Ellen Kuras, workedOn, Summer of Sam]
  • A. Summer of Sam chosen
    Summer of Sam is a 1999 crime thriller film directed by Spike Lee that dramatizes the fear and paranoia in New York City during the 1977 Son of Sam murders.
  • B. The Babysitter
    The Babysitter is a 2017 American horror-comedy film about a young boy who discovers his attractive babysitter is part of a satanic cult.
  • C. Night Trap
    Night Trap is a controversial 1992 interactive movie horror video game known for its full-motion video gameplay and its central role in early 1990s debates over video game violence and content regulation.
  • D. Pet Sematary
    Pet Sematary is a horror novel by Stephen King about a burial ground with the power to resurrect the dead, leading to terrifying consequences for a grieving family.
  • E. The Boogeyman
    "The Boogeyman" is a horror short story by Stephen King about a man recounting terrifying encounters with a child-killing monster to a psychiatrist.
  • 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_69bd43ed84648190ae0b7ee8e8d00482 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd64456a6c8190b658216b62ef82cf completed March 20, 2026, 3:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69be39ff21f0819094a273a0f26b22f4 completed March 21, 2026, 6:26 a.m.
Created at: March 20, 2026, 1:18 p.m.