Triple

T12402721
Position Surface form Disambiguated ID Type / Status
Subject Paul Mazursky E296297 entity
Predicate directed P7373 FINISHED
Object Moscow on the Hudson E977744 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: Moscow on the Hudson | Statement: [Paul Mazursky, directed, Moscow on the Hudson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Moscow on the Hudson
Context triple: [Paul Mazursky, directed, Moscow on the Hudson]
  • A. Moscow on the Hudson chosen
    Moscow on the Hudson is a 1984 comedy-drama film starring Robin Williams as a Soviet circus musician who defects to the United States, exploring themes of immigration and cultural adjustment.
  • B. Havana on the Hudson
    Havana on the Hudson is a nickname for Union City, New Jersey, reflecting its large Cuban-American community and vibrant Latin American culture.
  • C. Eiserner Steg
    Eiserner Steg is a historic pedestrian iron footbridge over the River Main in Frankfurt, known for its city views and love locks.
  • D. Tales from the Hudson
    Tales from the Hudson is a critically acclaimed 1996 jazz album by saxophonist Michael Brecker, noted for its modern post-bop compositions and all-star ensemble.
  • E. Big House on the Hudson
    Big House on the Hudson is a famous maximum-security prison in Ossining, New York, known historically for housing some of the United States’ most notorious criminals.
  • 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_69d6ad9f464c81909db36d7e96e34b9e completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d94d477004819095e65ef6f70c69d9 completed April 10, 2026, 7:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69f64b962d1c81909c2119890d921648 completed May 2, 2026, 7:08 p.m.
Created at: April 8, 2026, 9:55 p.m.