Triple

T7206733
Position Surface form Disambiguated ID Type / Status
Subject Roseanne E148683 entity
Predicate starring P1507 FINISHED
Object Sandra Bernhard E322078 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: Sandra Bernhard | Statement: [Roseanne, starring, Sandra Bernhard]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sandra Bernhard
Context triple: [Roseanne, starring, Sandra Bernhard]
  • A. Sandra Bernhard chosen
    Sandra Bernhard is an American comedian, actress, singer, and author known for her sharp, satirical stand-up and distinctive roles in film and television.
  • B. Cheri Oteri
    Cheri Oteri is an American comedian and actress best known as a cast member on "Saturday Night Live" in the late 1990s, where she created several popular recurring characters.
  • C. Marilu Henner
    Marilu Henner is an American actress and author best known for her role as Elaine Nardo on the TV sitcom "Taxi" and for her appearances in numerous film and television projects.
  • D. Susie Essman
    Susie Essman is an American stand-up comedian and actress best known for her sharp-tongued, foul-mouthed role as Susie Greene on the HBO comedy series "Curb Your Enthusiasm."
  • E. P. J. Soles
    P. J. Soles is an American actress best known for her roles in classic late-1970s and early-1980s films such as "Carrie," "Halloween," and various 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_69c687e8cf188190b5f3ecffd681f04e completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c6e969c5fc819096bc03bfba12d0cf completed March 27, 2026, 8:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7bfc0ac008190b3ea46b4e5f13287 completed March 28, 2026, 11:47 a.m.
Created at: March 27, 2026, 2:52 p.m.