Triple

T2890439
Position Surface form Disambiguated ID Type / Status
Subject Carl Sagan E63806 entity
Predicate spouse P13 FINISHED
Object Linda Salzman Sagan E2913 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: Linda Salzman Sagan | Statement: [Carl Sagan, spouse, Linda Salzman Sagan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Linda Salzman Sagan
Context triple: [Carl Sagan, spouse, Linda Salzman Sagan]
  • A. Linda Salzman Sagan chosen
    Linda Salzman Sagan is an American artist and writer best known for co-designing the Pioneer plaque and contributing to other interstellar message projects alongside Carl Sagan.
  • B. Roberta Seidman
    Roberta Seidman was the wife of American actor John Garfield, a prominent film star of the 1930s and 1940s.
  • C. Jennifer Margulis
    Jennifer Margulis is an American author and journalist known for her work on parenting, health, and social issues, including critiques of conventional medical and childcare practices.
  • D. Judith Nodine
    Judith Nodine is known as the former spouse of American investor and former U.S. Secretary of Commerce Wilbur Ross.
  • E. Gail Mutrux
    Gail Mutrux is an American film producer known for her work on acclaimed dramas such as "News of the World" and "Donnie Brasco."
  • 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_69ab4c45822c8190830c5f2bb97bcfd0 completed March 6, 2026, 9:51 p.m.
NER Named-entity recognition batch_69abe05f98848190a33344fa780a3597 completed March 7, 2026, 8:22 a.m.
NED1 Entity disambiguation (via context triple) batch_69b03179d7448190bcdbea164856aaa2 completed March 10, 2026, 2:58 p.m.
Created at: March 6, 2026, 10:07 p.m.