Triple

T15625018
Position Surface form Disambiguated ID Type / Status
Subject RED (2010 film) E375656 entity
Predicate mainCharacter P1183 FINISHED
Object Sarah Ross E848096 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: Sarah Ross | Statement: [RED (2010 film), mainCharacter, Sarah Ross]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sarah Ross
Context triple: [RED (2010 film), mainCharacter, Sarah Ross]
  • A. Sarah Ross chosen
    Sarah Ross is a retired CIA analyst drawn back into the world of espionage and action in the comedy-action film "Red 2."
  • B. Rose Ross
    Rose Ross is a central character in the 2015 Western film "Slow West," around whom much of the story’s journey and conflict revolve.
  • C. Charlotte Ross
    Charlotte Ross is an American actress best known for her television roles on series such as NYPD Blue, Days of Our Lives, and Glee.
  • D. Sarah Kirkpatrick
    Sarah Kirkpatrick was the wife of prominent 18th-century American Presbyterian minister and educator Samuel Davies.
  • E. Mary Brian Stapler Ross
    Mary Brian Stapler Ross was the wife of American Revolutionary War figure John Ross and a member of Philadelphia’s prominent Stapler family.
  • 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_69d85cd035a48190b73d5579ab73969a completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04e9e5e248190ae54cda1fde51efb completed April 16, 2026, 2:51 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff678c9d8c8190be73b6e7ed558e99 completed May 9, 2026, 4:57 p.m.
Created at: April 10, 2026, 4:14 a.m.