Triple

T19532702
Position Surface form Disambiguated ID Type / Status
Subject ATL (2006 film) E488693 entity
Predicate screenwriter P2831 FINISHED
Object Tina Gordon Chism 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: Tina Gordon Chism | Statement: [ATL (2006 film), screenwriter, Tina Gordon Chism]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tina Gordon Chism
Context triple: [ATL (2006 film), screenwriter, Tina Gordon Chism]
  • A. Tina Gordon Chism chosen
    Tina Gordon Chism is an American screenwriter and director known for her work on films such as Drumline, ATL, and Little, often highlighting Black culture and family dynamics.
  • B. Tina Graham
    Tina Graham is known as the wife of American bassist and singer Larry Graham, a pioneering figure in funk music and former member of Sly and the Family Stone.
  • C. Tina Wilcox
    Tina Wilcox is a fictional character portrayed by Ann Dusenberry, best known from the 1978 film "Jaws 2."
  • D. Cheryl Johnson
    Cheryl Johnson is the wife of American sportscaster Ernie Johnson Jr., known for her long-standing support of his broadcasting career and their family.
  • E. Tina Moss
    Tina Moss is known as the wife of the late American record executive and A&M Records co-founder Jerry Moss.
  • 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_69d8e8db5b6c8190984b61f91981f575 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e6364091f4819088b27d0ffdf6010d completed April 20, 2026, 2:20 p.m.
Created at: April 10, 2026, 1:41 p.m.