Triple

T8969165
Position Surface form Disambiguated ID Type / Status
Subject Russell Mulcahy E214217 entity
Predicate directedMusicVideo P4911 FINISHED
Object Betty Davis Eyes E113832 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: Betty Davis Eyes | Statement: [Russell Mulcahy, directedMusicVideo, Betty Davis Eyes]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Betty Davis Eyes
Context triple: [Russell Mulcahy, directedMusicVideo, Betty Davis Eyes]
  • A. Bette Davis Eyes chosen
    "Bette Davis Eyes" is a 1981 synth-driven pop song by Kim Carnes that became a global hit and is widely regarded as her signature recording.
  • B. Brown Eyed Girl
    "Brown Eyed Girl" is a 1967 pop-rock song by Van Morrison that became one of his signature hits and a classic of popular music.
  • C. New Eyes
    New Eyes is the debut studio album by British electronic music group Clean Bandit, featuring their hit single "Rather Be."
  • D. Gypsy Eyes
    "Gypsy Eyes" is a psychedelic rock song by the Jimi Hendrix Experience, featured on their 1968 double album *Electric Ladyland*.
  • E. In Your Eyes
    In Your Eyes is a 2014 romantic science-fiction film written by Joss Whedon about two strangers who share a mysterious telepathic bond.
  • 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_69ca839dbf608190a2f5990477115d29 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc6765babc8190a4a3b79aa21047c8 completed April 1, 2026, 12:31 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfc96006e48190978e4ccdedc48b41 completed April 3, 2026, 2:06 p.m.
Created at: March 30, 2026, 7:01 p.m.