Triple

T18146561
Position Surface form Disambiguated ID Type / Status
Subject Station to Station E434405 entity
Predicate engineer P184 FINISHED
Object Harry Maslin 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: Harry Maslin | Statement: [Station to Station, engineer, Harry Maslin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harry Maslin
Context triple: [Station to Station, engineer, Harry Maslin]
  • A. Harry Maslin chosen
    Harry Maslin is an American record producer and engineer best known for his work with David Bowie in the 1970s, including co-producing the albums "Young Americans" and "Station to Station."
  • B. Anthony Hollander
    Anthony Hollander is a British medical scientist known for his work in regenerative medicine and tissue engineering, particularly in pioneering stem-cell-based therapies.
  • C. Kevin Crowe
    Kevin Crowe is a songwriter best known for co-writing the hit track "Young, Wild & Free."
  • D. Ronald Moran
    Ronald "Ronnie" Moran was a long-serving Liverpool FC player and coach who became a legendary figure at the club for his decades of service and influence.
  • E. Lew Lipton
    Lew Lipton was an American screenwriter active during the early 20th century, known for his work in Hollywood silent and early sound films.
  • 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_69d8b90aac308190801e2c57d8c5bfe5 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4de34bb608190a4842e86f2912dec completed April 19, 2026, 1:52 p.m.
Created at: April 10, 2026, 10:29 a.m.