Triple

T10543004
Position Surface form Disambiguated ID Type / Status
Subject Mindy Sterling E248742 entity
Predicate givenName P17 FINISHED
Object Mindy E248742 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: Mindy | Statement: [Mindy Sterling, givenName, Mindy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mindy
Context triple: [Mindy Sterling, givenName, Mindy]
  • A. Mindy
    Mindy is a feminine given name most notably associated with American actress Mindy Cohn, known for her role on the TV series "The Facts of Life."
  • B. Mindy Sterling chosen
    Mindy Sterling is an American actress and comedian best known for her role as the villainous Frau Farbissina in the Austin Powers film series.
  • C. June Mindy
    June Mindy is a fictional character in the film "Don't Look Up," portrayed as the wife of astronomer Dr. Randall Mindy.
  • D. Mandie
    Mandie is a feminine given name, typically used as a variant spelling of Mandy or Amanda.
  • E. Melinda
    Melinda is the first name of Melinda French Gates, an American philanthropist and co-founder of the Bill & Melinda Gates Foundation.
  • 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_69d381c733c08190ab1dd6239f5f34ae completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d5190f46d08190a92b1191881ffb92 completed April 7, 2026, 2:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69d94b23b2988190b536d5ecb76298ff completed April 10, 2026, 7:10 p.m.
Created at: April 6, 2026, 12:32 p.m.