Triple

T23468003
Position Surface form Disambiguated ID Type / Status
Subject Table 19 E569147 entity
Predicate starring P1507 FINISHED
Object Lisa Kudrow 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: Lisa Kudrow | Statement: [Table 19, starring, Lisa Kudrow]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lisa Kudrow
Context triple: [Table 19, starring, Lisa Kudrow]
  • A. Lisa Kudrow chosen
    Lisa Kudrow is an American actress, comedian, writer, and producer best known for playing Phoebe Buffay on the television sitcom "Friends."
  • B. Kathryn Hahn
    Kathryn Hahn is an American actress and comedian known for her versatile roles in film and television, including prominent work in comedies and voice acting.
  • C. Kristen Schaal
    Kristen Schaal is an American actress, comedian, and voice artist known for her distinctive voice and roles in series like "Flight of the Conchords," "Bob's Burgers," and "The Last Man on Earth."
  • D. Sandra Corddry
    Sandra Corddry is the wife of American actor and comedian Rob Corddry, known for largely maintaining a private life outside of her husband's public career.
  • E. Anna Faris
    Anna Faris is an American actress and comedian best known for her lead role in the Scary Movie film series and her work in both film and television comedy.
  • 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_69e2458ebd808190b3298163132cfb0b completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1a6fd280c81908aae05f0851466eb completed April 29, 2026, 6:36 a.m.
Created at: April 17, 2026, 5:54 p.m.