Triple

T10396651
Position Surface form Disambiguated ID Type / Status
Subject Apple Tree Yard E245037 entity
Predicate executiveProducer P7225 FINISHED
Object Manda Levin E875022 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: Manda Levin | Statement: [Apple Tree Yard, executiveProducer, Manda Levin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Manda Levin
Context triple: [Apple Tree Yard, executiveProducer, Manda Levin]
  • A. Manda Levin chosen
    Manda Levin is a television producer known for her executive production work on the crime drama series "The Tunnel."
  • B. Rachel Leibowitz
    Rachel Leibowitz is a person notable enough to be specifically cited as a bearer of the surname Leibowitz.
  • C. Seryl Kushner
    Seryl Kushner is an American businesswoman and matriarch of the Kushner family, best known as the mother of real estate investor and former presidential advisor Jared Kushner.
  • D. Ilene Rosenzweig
    Ilene Rosenzweig is a writer and editor best known for co-authoring lifestyle and design books with fashion designer Cynthia Rowley.
  • E. Mimi Leder
    Mimi Leder is an American film and television director and producer known for her work on impactful dramas such as "Deep Impact," "The Leftovers," and "On the Basis of Sex."
  • 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_69d381b5116081908d85227bab6d3c0c completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4e9cf79348190975d6c1791e3b621 completed April 7, 2026, 11:26 a.m.
NED1 Entity disambiguation (via context triple) batch_69dbac97ce2481908ea11d6290a9bf2f completed April 12, 2026, 2:30 p.m.
Created at: April 6, 2026, 12:06 p.m.