Triple

T3884370
Position Surface form Disambiguated ID Type / Status
Subject Blackmail (1929 film) E92902 entity
Predicate stars P1956 FINISHED
Object Sara Allgood E346154 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: Sara Allgood | Statement: [Blackmail (1929 film), stars, Sara Allgood]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sara Allgood
Context triple: [Blackmail (1929 film), stars, Sara Allgood]
  • A. Sara Allgood chosen
    Sara Allgood was an Irish stage and film actress known for her character roles in early 20th-century theatre and classic Hollywood cinema.
  • B. Sara Henry
    Sara Henry is known as the wife of American voice actor and comedian Mike Henry, recognized for his work on shows like Family Guy.
  • C. Sara Haden
    Sara Haden was an American character actress best known for her supporting roles in classic Hollywood films of the 1930s and 1940s, including several entries in the Andy Hardy series.
  • D. Susan Allerton
    Susan Allerton was a member of the Allerton family associated with early colonial New England, known primarily as a sibling of Mayflower passenger Isaac Allerton.
  • E. Elizabeth Prall
    Elizabeth Prall was an American bookseller and literary figure best known for her marriage to modernist writer Sherwood Anderson.
  • 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_69aed9697de0819087c2559295ff3d12 completed March 9, 2026, 2:30 p.m.
NER Named-entity recognition batch_69aeec9029908190a7b36a3827734db1 completed March 9, 2026, 3:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5c6ed5910819095de0dce09bd50b8 completed March 14, 2026, 8:37 p.m.
Created at: March 9, 2026, 3:20 p.m.