Triple

T9400423
Position Surface form Disambiguated ID Type / Status
Subject Mackenzie Davis E226452 entity
Predicate notableWork P4 FINISHED
Object Always Shine
Always Shine is a 2016 psychological thriller film about two actresses whose friendship unravels during a tense trip to Big Sur.
E795671 NE FINISHED

How this triple was built (4 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: Always Shine | Statement: [Mackenzie Davis, notableWork, Always Shine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Always Shine
Context triple: [Mackenzie Davis, notableWork, Always Shine]
  • A. Dare to Shine
    Dare to Shine is the inspirational slogan used to promote the 2019 FIFA Women’s World Cup, emphasizing empowerment, excellence, and visibility in women’s football.
  • B. Shine Your Light
    "Shine Your Light" is a notable song by the band Blue Electric Light, recognized as one of their standout tracks.
  • C. Something Shines
    "Something Shines" is a solo studio album by French musician Laetitia Sadier, known for its atmospheric blend of avant-pop, indie, and politically tinged lyrics.
  • D. One Shine
    One Shine is a track by hip-hop band The Roots featured on their acclaimed 1996 album Illadelph Halflife.
  • E. Love Shine Brighter
    "Love Shine Brighter" is a song by International Herb, likely featuring their characteristic reggae-influenced, roots-inspired sound.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Always Shine
Triple: [Mackenzie Davis, notableWork, Always Shine]
Generated description
Always Shine is a 2016 psychological thriller film about two actresses whose friendship unravels during a tense trip to Big Sur.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Always Shine
Target entity description: Always Shine is a 2016 psychological thriller film about two actresses whose friendship unravels during a tense trip to Big Sur.
  • A. Dare to Shine
    Dare to Shine is the inspirational slogan used to promote the 2019 FIFA Women’s World Cup, emphasizing empowerment, excellence, and visibility in women’s football.
  • B. Shine Your Light
    "Shine Your Light" is a notable song by the band Blue Electric Light, recognized as one of their standout tracks.
  • C. Something Shines
    "Something Shines" is a solo studio album by French musician Laetitia Sadier, known for its atmospheric blend of avant-pop, indie, and politically tinged lyrics.
  • D. One Shine
    One Shine is a track by hip-hop band The Roots featured on their acclaimed 1996 album Illadelph Halflife.
  • E. Love Shine Brighter
    "Love Shine Brighter" is a song by International Herb, likely featuring their characteristic reggae-influenced, roots-inspired sound.
  • F. None of above. chosen

Provenance (5 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_69ca843170f88190800a8ab2b5fc568e completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd5156b9588190bafb6b1c3ee3c0ed completed April 1, 2026, 5:09 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1012753088190bc73b7c577109e76 completed April 4, 2026, 12:16 p.m.
NEDg Description generation batch_69d101aee16481909576ea5d8407beb5 completed April 4, 2026, 12:18 p.m.
NED2 Entity disambiguation (via description) batch_69d1024cfedc81908a97b5fe4970719a completed April 4, 2026, 12:21 p.m.
Created at: March 30, 2026, 7:46 p.m.