Triple

T20469789
Position Surface form Disambiguated ID Type / Status
Subject Audrey Paris E502159 entity
Predicate portrayedBy P1507 FINISHED
Object Leland Palmer 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: Leland Palmer | Statement: [Audrey Paris, portrayedBy, Leland Palmer]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Leland Palmer
Context triple: [Audrey Paris, portrayedBy, Leland Palmer]
  • A. Leland Palmer chosen
    Leland Palmer is an American actress, singer, and dancer best known for her work in musical theatre and film during the 1960s and 1970s.
  • B. Leland Palmer
    Leland Palmer is a central character in the television series "Twin Peaks," known as Laura Palmer’s troubled father whose unraveling psyche and dark secrets drive much of the show’s mystery and horror.
  • C. Leland Patton
    Leland Patton is a theatre professional best known as a founder of the Crossroads Theatre Company, a prominent African-American theater organization.
  • D. Leland McKenzie
    Leland McKenzie is a senior partner and authoritative yet principled lawyer at the fictional Los Angeles law firm in the television series "L.A. Law."
  • E. Charles Noland
    Charles Noland is an American actor known for his character roles in film, television, and theater.
  • 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_69e0b4ae5f1081908768b0c9a3a0bf38 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6995f753081909bbe03f7c251d9c1 completed April 20, 2026, 9:23 p.m.
Created at: April 16, 2026, 11:33 a.m.