Triple

T21713322
Position Surface form Disambiguated ID Type / Status
Subject The Kremlin Letter E535959 entity
Predicate screenwriter P2831 FINISHED
Object Gladys Hill NE NERFINISHED

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: Gladys Hill | Statement: [The Kremlin Letter, screenwriter, Gladys Hill]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gladys Hill
Context triple: [The Kremlin Letter, screenwriter, Gladys Hill]
  • A. Gladys Hill chosen
    Gladys Hill was an American screenwriter best known for co-writing the acclaimed 1975 adventure film "The Man Who Would Be King," directed by John Huston.
  • B. Gladys Malvern
    Gladys Malvern was an American author and illustrator best known for her historical and biographical novels for young adults, often featuring strong female protagonists.
  • C. Gladys Horton
    Gladys Horton was an American singer best known as the lead vocalist and a founding member of the Motown girl group The Marvelettes, who scored hits like "Please Mr. Postman."
  • D. Gloria Hill
    Gloria Hill is known as the wife of prominent American television and film producer David L. Wolper.
  • E. Marion Hill
    Marion Hill is the charming, wisecracking former football player and single father at the center of the 1990s sitcom "In the House."
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0c46c6dd88190a595375fa6ebd701 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69efb53573a08190ad73576d27e8094f completed April 27, 2026, 7:12 p.m.
Created at: April 16, 2026, 6:47 p.m.