Triple

T20384087
Position Surface form Disambiguated ID Type / Status
Subject Thoroughbreds Don’t Cry E497915 entity
Predicate director P255 FINISHED
Object Alfred E. Green — 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: Alfred E. Green | Statement: [Thoroughbreds Don’t Cry, director, Alfred E. Green]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Alfred E. Green
Context triple: [Thoroughbreds Don’t Cry, director, Alfred E. Green]
  • A. Alfred E. Green chosen
    Alfred E. Green was an American film director active from the silent era through the mid-20th century, known for directing numerous Hollywood features across a variety of genres.
  • B. Albert C. Greene
    Albert C. Greene was a 19th-century American politician and lawyer who served as a U.S. Senator from Rhode Island.
  • C. G. C. Green
    G. C. Green is an English bassist best known as a founding member of the industrial metal band Godflesh.
  • D. Frederick W. Green
    Frederick W. Green was a British Egyptologist known for his archaeological work and excavations in Egypt during the late 19th and early 20th centuries.
  • E. William Edward Green
    William Edward Green, better known as William Friese-Greene, was a pioneering British inventor and early motion picture experimenter credited with significant contributions to the development of cinematography.
  • 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_69e0b4a5b7908190a972e4e7e698ae94 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e678b2ceec819091ad5205ee9b2174 completed April 20, 2026, 7:04 p.m.
Created at: April 16, 2026, 11:27 a.m.