Triple

T7652836
Position Surface form Disambiguated ID Type / Status
Subject Susan Goldmark E173297 entity
Predicate spouse P13 FINISHED
Object Kai Bird E8984 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: Kai Bird | Statement: [Susan Goldmark, spouse, Kai Bird]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kai Bird
Context triple: [Susan Goldmark, spouse, Kai Bird]
  • A. Kai Bird chosen
    Kai Bird is an American historian, biographer, and Pulitzer Prize–winning author best known for co-writing the J. Robert Oppenheimer biography "American Prometheus."
  • B. Hampton Sides
    Hampton Sides is an American historian and bestselling narrative nonfiction author known for his gripping accounts of exploration, war, and adventure.
  • C. Lawrence Wright
    Lawrence Wright is an American journalist, author, and screenwriter best known for his Pulitzer Prize-winning investigative nonfiction works on topics such as terrorism and Scientology.
  • D. Alec Ross
    Alec Ross was a British actor and the first husband of actress Sheila Hancock, known for his work on stage and screen before his early death from esophageal cancer.
  • E. Eric Larson
    Eric Larson was a prominent American animator and one of Disney’s legendary “Nine Old Men,” known for his influential work on many classic Disney films.
  • 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_69c6995473348190a4f41d110d619a18 completed March 27, 2026, 2:51 p.m.
NER Named-entity recognition batch_69c7018c34a88190be6089a9105bd4b0 completed March 27, 2026, 10:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69c89aeb66c081909f3a3d6385637c25 completed March 29, 2026, 3:22 a.m.
Created at: March 27, 2026, 3:58 p.m.