Triple

T18615407
Position Surface form Disambiguated ID Type / Status
Subject Don’t Let the Stars Get in Your Eyes E455007 entity
Predicate notableRecordingBy P1152 FINISHED
Object Gisele MacKenzie NE NERFINISHED

How this triple was built (3 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: Gisele MacKenzie | Statement: [Don’t Let the Stars Get in Your Eyes, notableRecordingBy, Gisele MacKenzie]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gisele MacKenzie
Context triple: [Don’t Let the Stars Get in Your Eyes, notableRecordingBy, Gisele MacKenzie]
  • A. Laura Montez
    Laura Montez is a charismatic and politically ambitious U.S. politician in the TV series "Veep," who emerges as a major competitor and foil to Selina Meyer.
  • B. Linda Evangelista
    Linda Evangelista is a Canadian supermodel renowned as one of the most prominent faces of the 1990s fashion industry and a key member of the original “supermodel” era.
  • C. Diana Sands
    Diana Sands was an acclaimed American stage and screen actress best known for her groundbreaking performance in the original Broadway production and film adaptation of "A Raisin in the Sun."
  • D. Lauren Hutton
    Lauren Hutton is an American model and actress known for her gap-toothed smile and pioneering status as one of the first supermodels, as well as for her roles in films such as "American Gigolo."
  • E. Elizabeth Dailey
    Elizabeth Dailey is known primarily as the spouse of American actor and dancer Dan Dailey.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Gisele MacKenzie
Target entity description: Gisele MacKenzie was a Canadian singer and television personality best known for her popular vocal performances in the 1950s, including several hit recordings and frequent appearances on variety shows.
  • A. Laura Montez
    Laura Montez is a charismatic and politically ambitious U.S. politician in the TV series "Veep," who emerges as a major competitor and foil to Selina Meyer.
  • B. Linda Evangelista
    Linda Evangelista is a Canadian supermodel renowned as one of the most prominent faces of the 1990s fashion industry and a key member of the original “supermodel” era.
  • C. Diana Sands
    Diana Sands was an acclaimed American stage and screen actress best known for her groundbreaking performance in the original Broadway production and film adaptation of "A Raisin in the Sun."
  • D. Lauren Hutton
    Lauren Hutton is an American model and actress known for her gap-toothed smile and pioneering status as one of the first supermodels, as well as for her roles in films such as "American Gigolo."
  • E. Elizabeth Dailey
    Elizabeth Dailey is known primarily as the spouse of American actor and dancer Dan Dailey.
  • F. None of above. chosen

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_69d8d38bbe7c8190bdec3138e7d413c9 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e54d04bdc48190b0213132923a7580 completed April 19, 2026, 9:45 p.m.
Created at: April 10, 2026, 11:45 a.m.