Triple

T11235768
Position Surface form Disambiguated ID Type / Status
Subject Cranford E265936 entity
Predicate writer P1360 FINISHED
Object Heidi Thomas E882377 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: Heidi Thomas | Statement: [Cranford, writer, Heidi Thomas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Heidi Thomas
Context triple: [Cranford, writer, Heidi Thomas]
  • A. Heidi Thomas chosen
    Heidi Thomas is a British screenwriter and playwright best known for creating and writing the acclaimed period drama series "Call the Midwife."
  • B. June Roberts
    June Roberts is a screenwriter known for her work on the film "Mermaids."
  • C. Carolyn Jones
    Carolyn Jones is a former American professional women's basketball player best known for her standout career in the ABL and WNBA during the 1990s.
  • D. Carolyn Jones
    Carolyn Jones was an American actress best known for her iconic portrayal of Morticia Addams in the 1960s television series "The Addams Family."
  • E. Lorraine Bailey
    Lorraine Bailey was the proprietor of the historic Lorraine Motel in Memphis, Tennessee, later known as the site of Dr. Martin Luther King Jr.'s assassination and now part of the National Civil Rights Museum.
  • 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_69d6aac656d48190b275efaa7d6074ee completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e904cf888190826fc964f76b5cb2 completed April 9, 2026, 5:59 p.m.
NED1 Entity disambiguation (via context triple) batch_69e542ab02708190b40a96edd56a6519 completed April 19, 2026, 9:01 p.m.
Created at: April 8, 2026, 9:30 p.m.