Triple

T14002711
Position Surface form Disambiguated ID Type / Status
Subject Valerie Harper E336869 entity
Predicate birthName P65 FINISHED
Object Valerie Kathryn Harper E336869 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: Valerie Kathryn Harper | Statement: [Valerie Harper, birthName, Valerie Kathryn Harper]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Valerie Kathryn Harper
Context triple: [Valerie Harper, birthName, Valerie Kathryn Harper]
  • A. Valerie Harper chosen
    Valerie Harper was an American actress best known for her Emmy-winning role as the sharp-witted Rhoda Morgenstern on television in the 1970s.
  • B. Patricia Heaton
    Patricia Heaton is an American actress best known for her role as Debra Barone on the hit sitcom "Everybody Loves Raymond."
  • C. Amy Brenneman
    Amy Brenneman is an American actress and producer best known for her roles in television series such as "NYPD Blue," "Judging Amy," and "The Leftovers."
  • D. Michelle Bridget Farmer
    Michelle Bridget Farmer is the daughter of iconic American silent film star and Hollywood legend Gloria Swanson.
  • E. Mary Steenburgen
    Mary Steenburgen is an American actress known for her versatile performances in film and television, including acclaimed roles in movies such as "Melvin and Howard," "Back to the Future Part III," and numerous character-driven dramas and comedies.
  • 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_69d81c645c5c8190b1fd16a285a1b78a completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2ed06a50819093ddc64f55050689 completed April 14, 2026, 12:10 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcb652305c81908ea097d4f36a05c0 completed May 7, 2026, 3:57 p.m.
Created at: April 9, 2026, 10:19 p.m.