Triple

T7850671
Position Surface form Disambiguated ID Type / Status
Subject Cocoon E182042 entity
Predicate author P4 FINISHED
Object David Saperstein E182042 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: David Saperstein | Statement: [Cocoon, author, David Saperstein]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: David Saperstein
Context triple: [Cocoon, author, David Saperstein]
  • A. David Saperstein chosen
    David Saperstein is an American author best known for writing the science fiction novel "Cocoon," which was adapted into the popular 1985 film of the same name.
  • B. William Sheinberg
    William Sheinberg is known primarily as the son of influential Hollywood executive Sidney Sheinberg.
  • C. Steven Fierberg
    Steven Fierberg is an American cinematographer known for his work on feature films and television series, including the romantic drama "Love & Other Drugs."
  • D. David B. Cornstein
    David B. Cornstein is an American businessman and Republican political appointee who served as the U.S. Ambassador to Hungary under President Donald Trump.
  • E. Eric Tannenbaum
    Eric Tannenbaum is a television producer best known for his work on popular American sitcoms, including serving as an executive producer on "Two and a Half Men."
  • 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_69ca82869ee08190b8f9040dbc2c0467 completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cb18eaac508190bf373b1d50b52e1e completed March 31, 2026, 12:44 a.m.
NED1 Entity disambiguation (via context triple) batch_69cde6a2bdd08190897705615109dae0 completed April 2, 2026, 3:46 a.m.
Created at: March 30, 2026, 4:50 p.m.