Triple

T20100839
Position Surface form Disambiguated ID Type / Status
Subject Angus Mullens E496531 entity
Predicate workTitle P24259 FINISHED
Object Starstruck 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: Starstruck | Statement: [Angus Mullens, workTitle, Starstruck]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Starstruck
Context triple: [Angus Mullens, workTitle, Starstruck]
  • A. Starstruck chosen
    Starstruck is a 1982 Australian musical comedy film about a teenage girl who dreams of becoming a pop star in Sydney’s vibrant early-1980s music scene.
  • B. Love Star
    "Love Star" is a soulful, politically conscious track by Common from his album "Black America Again," blending introspective lyrics with rich, melodic production.
  • C. Maps to the Stars
    Maps to the Stars is a 2014 satirical drama film directed by David Cronenberg that explores the dark underbelly of Hollywood celebrity culture.
  • D. Another Star
    "Another Star" is an upbeat, horn-driven soul and funk song by Stevie Wonder from his acclaimed 1976 album "Songs in the Key of Life."
  • E. Starcrossed
    Starcrossed is a crime novel by British author Belinda Bauer, known for its dark humor and unconventional, character-driven twist on the psychological thriller.
  • 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_69da626eee3881909f3454986d4a6511 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e6666ff4008190ae1eec907c89bd3b completed April 20, 2026, 5:46 p.m.
Created at: April 11, 2026, 11:26 p.m.