Triple

T13920032
Position Surface form Disambiguated ID Type / Status
Subject Brian Taylor E334717 entity
Predicate directed P7373 FINISHED
Object Mom and Dad E1069617 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: Mom and Dad | Statement: [Brian Taylor, directed, Mom and Dad]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mom and Dad
Context triple: [Brian Taylor, directed, Mom and Dad]
  • A. Mom and Dad chosen
    "Mom and Dad" is a 2017 dark comedy horror film written and directed by Brian Taylor, in which parents suddenly become violently compelled to kill their own children.
  • B. Daddy
    "Daddy" is a critically acclaimed 1989 Indian drama film featuring Anupam Kher in one of his most celebrated roles, portraying an alcoholic father seeking redemption and reconciliation with his daughter.
  • C. Daddy
    "Daddy" is a popular jazz and pop standard from the early 1940s, best known through recordings by artists like Sammy Kaye and Julie London.
  • D. Daddy
    "Daddy" is a song featured on the album *Wanderland* by American singer-songwriter Kelis.
  • E. Daddy
    "Daddy" is a powerful and controversial confessional poem by Sylvia Plath that explores themes of trauma, oppression, and the speaker’s fraught relationship with her father.
  • 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_69d81c5f739081908bc05b2461f54828 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2aa428ac819084e7c4b244d15f20 completed April 14, 2026, 11:53 a.m.
NED1 Entity disambiguation (via context triple) batch_69fba1c45ba4819096233570d8d4afec completed May 6, 2026, 8:17 p.m.
Created at: April 9, 2026, 10:16 p.m.