Triple

T9722942
Position Surface form Disambiguated ID Type / Status
Subject Samuel Parris E235523 entity
Predicate hasChild P369 FINISHED
Object Elizabeth Parris E75989 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: Elizabeth Parris | Statement: [Samuel Parris, hasChild, Elizabeth Parris]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Elizabeth Parris
Context triple: [Samuel Parris, hasChild, Elizabeth Parris]
  • A. Elizabeth Parris chosen
    Elizabeth Parris was the young daughter of Salem Village minister Samuel Parris, whose strange afflictions in 1692 helped spark the Salem witch trials.
  • B. Lucy Warriner
    Lucy Warriner is the witty, sophisticated socialite at the center of the classic screwball comedy "The Awful Truth," known for her sharp banter and tumultuous romantic entanglements.
  • C. Hazel Bennet
    Hazel Bennet was the wife of American film director and actor Lloyd Bacon, associated with Hollywood’s early studio era.
  • D. Mary Forward
    Mary Forward was the wife of prominent 19th-century American lawyer and U.S. Attorney General Jeremiah Sullivan Black.
  • E. Sylvia Lowry
    Sylvia Lowry was an American advocate for the blind who founded the nonprofit organization Recording for the Blind (now Learning Ally) to provide accessible audiobooks for visually impaired students.
  • 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_69ca84d0123c819096f9dc3b6abb0881 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cd9e75abd48190a6e6679ec51496e8 completed April 1, 2026, 10:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1afb089e48190a14ed0c0f81872c7 completed April 5, 2026, 12:41 a.m.
Created at: March 30, 2026, 8:20 p.m.