Triple

T21587109
Position Surface form Disambiguated ID Type / Status
Subject The Shadow of Your Smile E532678 entity
Predicate writtenForFilm P36923 FINISHED
Object The Sandpiper 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: The Sandpiper | Statement: [The Shadow of Your Smile, writtenForFilm, The Sandpiper]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: The Sandpiper
Context triple: [The Shadow of Your Smile, writtenForFilm, The Sandpiper]
  • A. The Sandpiper chosen
    The Sandpiper is a 1965 romantic drama film starring Elizabeth Taylor and Richard Burton, best known for its Malibu setting and the Oscar-winning song "The Shadow of Your Smile."
  • B. Sanderling
    Sanderling is a German surname most notably associated with conductor Kurt Sanderling and his musically accomplished family.
  • C. The Lark
    The Lark is a stage play best known for featuring Julie Harris in a celebrated portrayal of Joan of Arc.
  • D. The Lark
    "The Lark" is a lyrical piano piece, often associated with Romantic-era Russian repertoire, known for its delicate, songlike melody and evocative, birdlike figurations.
  • E. The Swallow
    The Swallow is the English title of Giacomo Puccini’s opera "La rondine," a lyrical work that blends elements of opera and operetta.
  • 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_69e0c46251648190876f0427cf2d321b completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69eeeb6137fc8190840b7c1275e62a1d completed April 27, 2026, 4:51 a.m.
Created at: April 16, 2026, 6:31 p.m.