Triple

T21378057
Position Surface form Disambiguated ID Type / Status
Subject Mary Richards E527264 entity
Predicate friend P8712 FINISHED
Object Phyllis Lindstrom 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: Phyllis Lindstrom | Statement: [Mary Richards, friend, Phyllis Lindstrom]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Phyllis Lindstrom
Context triple: [Mary Richards, friend, Phyllis Lindstrom]
  • A. Phyllis Lindstrom chosen
    Phyllis Lindstrom is a snobbish, self-absorbed yet comically endearing neighbor and friend in the classic American sitcom "The Mary Tyler Moore Show."
  • B. Phyllis Housen
    Phyllis Housen is a film editor known for her work on the movie "Clemency."
  • C. Lenore Mills
    Lenore Mills is the protagonist of the film "Taken," around whom the story’s kidnapping and rescue plot revolves.
  • D. Diane Millstead
    Diane Millstead is an Australian academic and writer best known as the former wife of comedian and satirist Barry Humphries.
  • E. Diane Millstead
    Diane Millstead is the mother of Australian art dealer and journalist Oscar Humphries.
  • 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_69e0b51f363c8190944000ab5523b02b completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e8b0ca5e1c81909b06958459c553dc completed April 22, 2026, 11:28 a.m.
Created at: April 16, 2026, 5:11 p.m.