Triple

T3815021
Position Surface form Disambiguated ID Type / Status
Subject Molly Pitcher E84230 entity
Predicate possibleIdentity P13264 FINISHED
Object Mary Ludwig Hays E391788 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: Mary Ludwig Hays | Statement: [Molly Pitcher, possibleIdentity, Mary Ludwig Hays]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mary Ludwig Hays
Context triple: [Molly Pitcher, possibleIdentity, Mary Ludwig Hays]
  • A. Mary Ludwig Hays chosen
    Mary Ludwig Hays, popularly known as Molly Pitcher, was a heroine of the American Revolutionary War famed for carrying water to soldiers and reportedly taking over her husband's cannon during battle.
  • B. Mary Stone Hays
    Mary Stone Hays was the wife of influential American politician and film industry figure Will H. Hays, known for her role in his personal and social life.
  • C. Lydia Reed
    Lydia Reed is an American former child actress best known for her film and television roles in the 1950s.
  • D. Lucinda Southworth
    Lucinda Southworth is an American research scientist and philanthropist best known as the wife of Google co-founder Larry Page.
  • E. Sarah Towne Cloyce
    Sarah Towne Cloyce was a woman accused of witchcraft during the Salem witch trials, known for surviving the ordeal and later helping to restore the reputations of the condemned.
  • 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_69aed931f5908190be2c07af66d4df25 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aee8de9e948190bf461e55ad00eddb completed March 9, 2026, 3:35 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5121f9d288190bd265a95b7727ab5 completed March 14, 2026, 7:45 a.m.
Created at: March 9, 2026, 3:17 p.m.