Triple

T21889375
Position Surface form Disambiguated ID Type / Status
Subject Ruth Fisher E540495 entity
Predicate relative P37 FINISHED
Object Maya Fisher 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: Maya Fisher | Statement: [Ruth Fisher, relative, Maya Fisher]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Maya Fisher
Context triple: [Ruth Fisher, relative, Maya Fisher]
  • A. Maya Fisher chosen
    Maya Fisher is a minor character from the television series "Six Feet Under," known as the young daughter of main character Nate Fisher.
  • B. Maya Bennett
    Maya Bennett is the daughter of neonatal surgeon Dr. Naomi Bennett in the television series "Private Practice."
  • C. Maya Bishop
    Maya Bishop is a driven and skilled firefighter and former Olympic athlete who serves as a central protagonist and eventual captain on the television drama "Station 19."
  • D. Maya Corwin
    Maya Corwin is the daughter of American wildlife biologist and television host Jeff Corwin.
  • E. Maya Wilkes
    Maya Wilkes is a central character on the sitcom "Girlfriends," known for her sharp wit, strong opinions, and journey balancing friendship, family, and career.
  • 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_69e0c47a95908190ae3e19b716accb3d completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f118ef2b648190bbd78f6b3958d2ee completed April 28, 2026, 8:30 p.m.
Created at: April 16, 2026, 7:06 p.m.