Triple

T9044350
Position Surface form Disambiguated ID Type / Status
Subject Ray Conniff E216716 entity
Predicate notableWork P4 FINISHED
Object Somewhere My Love E556920 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: Somewhere My Love | Statement: [Ray Conniff, notableWork, Somewhere My Love]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Somewhere My Love
Context triple: [Ray Conniff, notableWork, Somewhere My Love]
  • A. Somewhere My Love chosen
    "Somewhere My Love" is a popular vocal adaptation of "Lara's Theme" from the film Doctor Zhivago, widely known for its romantic melody and nostalgic lyrics.
  • B. Somebody Loves Me
    "Somebody Loves Me" is a 1952 musical biographical film starring Betty Hutton as vaudeville and Broadway star Blossom Seeley.
  • C. Somebody Took My Love
    "Somebody Took My Love" is a song featured on the album "What About Me."
  • D. Be My Love
    "Be My Love" is a popular romantic song from the 1950 film "The Toast of New Orleans," best known for Mario Lanza’s hit recording and its enduring status as a classic vocal standard.
  • E. The One I Love
    The One I Love is a 2014 American surreal romantic dramedy film starring Mark Duplass and Elisabeth Moss, centered on a troubled couple whose weekend retreat takes an unexpectedly bizarre turn.
  • 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_69ca83d22d488190adbce5e020e9cd1d completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cc6b137cec8190bd1b812c10d9542a completed April 1, 2026, 12:47 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfebada5948190add8813ba547647f completed April 3, 2026, 4:32 p.m.
Created at: March 30, 2026, 7:09 p.m.