Triple

T22101746
Position Surface form Disambiguated ID Type / Status
Subject The Man in the Sky E546187 entity
Predicate starredActor P5563 FINISHED
Object Jack Hawkins 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: Jack Hawkins | Statement: [The Man in the Sky, starredActor, Jack Hawkins]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jack Hawkins
Context triple: [The Man in the Sky, starredActor, Jack Hawkins]
  • A. Jack Hawkins chosen
    Jack Hawkins was a distinguished British actor known for his commanding presence in mid-20th-century war and historical films.
  • B. Trevor Howard
    Trevor Howard was a distinguished English film and stage actor best known for his roles in classic films such as "Brief Encounter" and "The Third Man."
  • C. Michael Wilding
    Michael Wilding was a British film and stage actor best known for his roles in 1940s–1950s British cinema and for his high-profile marriage to actress Elizabeth Taylor.
  • D. George Powell
    George Powell was a 19th-century British sealer and explorer noted for his Antarctic voyages and co-discovery of several sub-Antarctic islands.
  • E. Jack Cardiff
    Jack Cardiff was an acclaimed British cinematographer and director renowned for his pioneering use of Technicolor and visually striking work on classic 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_69e11e378dc08190896d6a51597afd5a completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f129163b908190b63ace06016f4db8 completed April 28, 2026, 9:39 p.m.
Created at: April 16, 2026, 8:30 p.m.