Triple

T3682812
Position Surface form Disambiguated ID Type / Status
Subject Albert Szent-Györgyi E78148 entity
Predicate spouse P13 FINISHED
Object Marcia Houston E143591 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: Marcia Houston | Statement: [Albert Szent-Györgyi, spouse, Marcia Houston]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marcia Houston
Context triple: [Albert Szent-Györgyi, spouse, Marcia Houston]
  • A. Tamara Houston chosen
    Tamara Houston is best known as the wife of former NBA All-Star shooting guard Allan Houston.
  • B. Nellie Connally
    Nellie Connally was the First Lady of Texas and wife of Governor John Connally, best known for riding in the presidential limousine during the assassination of President John F. Kennedy in Dallas in 1963.
  • C. Patricia Haines
    Patricia Haines was a British actress known for her television and film roles in the 1950s and 1960s.
  • D. Madge Gates Wallace
    Madge Gates Wallace was the mother of Bess Truman and mother-in-law of U.S. President Harry S. Truman, known for her strong personality and complex relationship with her son-in-law.
  • E. Claudia Alta Johnson
    Claudia Alta "Lady Bird" Johnson was the First Lady of the United States from 1963 to 1969, known for her environmental beautification efforts and advocacy for conservation and highway landscape programs.
  • 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_69ad85e18c1c8190be8aafb227f39f48 completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc4948cc48190ab1f59cc4a2437cc completed March 8, 2026, 6:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4daffd6bc81908ac7a4b8b4073bc0 completed March 14, 2026, 3:50 a.m.
Created at: March 8, 2026, 3:25 p.m.