Triple

T13881820
Position Surface form Disambiguated ID Type / Status
Subject Ernest Lehman E333734 entity
Predicate wroteScreenplayFor P15305 FINISHED
Object Sabrina E110213 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: Sabrina | Statement: [Ernest Lehman, wroteScreenplayFor, Sabrina]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sabrina
Context triple: [Ernest Lehman, wroteScreenplayFor, Sabrina]
  • A. Sabrina chosen
    Sabrina is a classic 1954 romantic comedy film directed by Billy Wilder, starring Audrey Hepburn, Humphrey Bogart, and William Holden in a Cinderella-like tale of love and transformation.
  • B. Sabrina
    Sabrina is the granddaughter of Iris Chase, a central character in Margaret Atwood’s novel "The Blind Assassin."
  • C. Sabrina
    Sabrina is a feminine given name of Latin origin meaning "from the River Severn," used in various cultures around the world.
  • D. Sabrina Fair
    Sabrina Fair is a romantic comedy play by Samuel Taylor that inspired the classic Audrey Hepburn film "Sabrina."
  • E. Sabrina Le Beauf
    Sabrina Le Beauf is an American actress best known for playing Sondra Huxtable on the hit television sitcom "The Cosby Show."
  • 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_69f7ce6facd48190b310099fbd52bdf0 completed May 3, 2026, 10:38 p.m.
Created at: April 9, 2026, 10:15 p.m.