Triple

T14628188
Position Surface form Disambiguated ID Type / Status
Subject Herbert Streicher E343407 entity
Predicate stageName P7872 FINISHED
Object Harry Reems E167076 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: Harry Reems | Statement: [Herbert Streicher, stageName, Harry Reems]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harry Reems
Context triple: [Herbert Streicher, stageName, Harry Reems]
  • A. Harry Reems chosen
    Harry Reems was an American adult film actor best known for his leading role in the landmark 1972 pornographic film "Deep Throat."
  • B. Stanley Reames
    Stanley Reames was the first husband of American actress Janet Leigh, to whom she was briefly married before her later, more famous marriages.
  • C. Harry Kullijian
    Harry Kullijian was an American businessman and civic activist best known as the late-life husband and partner of Broadway star Carol Channing.
  • D. Harry Zohn
    Harry Zohn was an Austrian-born American translator and scholar best known for his influential English translations of Walter Benjamin’s essays and other works of German literature and critical theory.
  • E. Harry Hyams
    Harry Hyams was a British property developer best known for his controversial large-scale commercial projects in central London during the postwar period.
  • 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_69d822dffc3c8190aa173b90761bffda completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb4a7c8fc81909d10c1f563d7d1e7 completed April 14, 2026, 9:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69fda92c25ac8190ba931c009e7ace19 completed May 8, 2026, 9:13 a.m.
Created at: April 10, 2026, 1:26 a.m.