Triple

T20088227
Position Surface form Disambiguated ID Type / Status
Subject George Allen E496193 entity
Predicate spouse P13 FINISHED
Object Susan Allen 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: Susan Allen | Statement: [George Allen, spouse, Susan Allen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Susan Allen
Context triple: [George Allen, spouse, Susan Allen]
  • A. Susan Allen chosen
    Susan Allen is an American public figure best known as the wife of former Virginia governor and U.S. senator George Allen.
  • B. Marilyn Vance
    Marilyn Vance is an American costume designer known for her influential work on numerous popular films, including iconic 1980s and 1990s movies.
  • C. Martie Allen
    Martie Allen is an American woman best known as the long-term partner of former child star and Emmy-winning actress Kristy McNichol.
  • D. Amy Lou Adams
    Amy Lou Adams is an acclaimed American actress known for her versatile performances in both comedic and dramatic films, including roles in "Enchanted," "American Hustle," and "Arrival."
  • E. Sandy Rogers
    Sandy Rogers is one of the adopted children of American singer, actress, and cowgirl icon Dale Evans and her husband Roy Rogers.
  • 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_69da626eee3881909f3454986d4a6511 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e6655c7de081909a400c736e92495d completed April 20, 2026, 5:41 p.m.
Created at: April 11, 2026, 11:16 p.m.