Triple

T8975452
Position Surface form Disambiguated ID Type / Status
Subject Mary Theresa Mehegan Hill E214375 entity
Predicate givenName P17 FINISHED
Object Mary
Mary is a feminine given name of Hebrew origin that has been widely used across cultures and history, often associated with religious and historical figures.
E75782 NE FINISHED

How this triple was built (4 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 | Statement: [Mary Theresa Mehegan Hill, givenName, Mary]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mary
Context triple: [Mary Theresa Mehegan Hill, givenName, Mary]
  • A. Mary
    Mary is a central figure in Christianity, venerated as the mother of Jesus and often honored as the Virgin Mary.
  • B. Mary
    Mary is the given first name of Margaret Truman, the daughter of U.S. President Harry S. Truman and a noted author and singer.
  • C. Mary
    Mary is the given name of the American suspense novelist Mary Higgins Clark, known for her bestselling mystery and thriller books.
  • D. Mary
    Mary is the middle name of Katherine Mary Dewar, a component of her full personal name.
  • E. Mary
    Mary Allerton was a Mayflower passenger and one of the early settlers of Plymouth Colony in 17th-century New England.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Mary
Triple: [Mary Theresa Mehegan Hill, givenName, Mary]
Generated description
Mary is a feminine given name of Hebrew origin that has been widely used across cultures and history, often associated with religious and historical figures.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mary
Target entity description: Mary is a feminine given name of Hebrew origin that has been widely used across cultures and history, often associated with religious and historical figures.
  • A. Mary chosen
    Mary is a feminine given name of Hebrew origin, widely used in English-speaking and many other cultures and historically associated with numerous religious and historical figures.
  • B. Mary
    Mary is the given name of Mary Anne Galton, a historical figure known primarily through her familial and biographical associations.
  • C. Mary
    Mary is a central figure in Christianity, venerated as the mother of Jesus and often honored as the Virgin Mary.
  • D. Mary
    Mary is the given name of Mary Wollstonecraft, the pioneering 18th-century English writer and advocate of women's rights.
  • E. Mary
    Mary is the given name of Mary Sidney, an English Renaissance noblewoman, writer, and literary patron.
  • F. None of above.

Provenance (5 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_69ca839ea8b88190922c6a326ffcc0d3 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc6784d1808190899c980f76084ff8 completed April 1, 2026, 12:32 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfd0afe9688190bdd66198ab31c2c7 completed April 3, 2026, 2:37 p.m.
NEDg Description generation batch_69cfd14a28d48190b63561f9a537daeb completed April 3, 2026, 2:40 p.m.
NED2 Entity disambiguation (via description) batch_69cfd1fd6db08190921285c3cfd3ce91 completed April 3, 2026, 2:43 p.m.
Created at: March 30, 2026, 7:02 p.m.