Triple

T16064105
Position Surface form Disambiguated ID Type / Status
Subject Mary Winsor E389689 entity
Predicate givenName P17 FINISHED
Object Mary
Mary is a feminine given name of Hebrew origin, traditionally interpreted to mean "beloved" or "bitter," and has been widely used across cultures and centuries.
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 Winsor, givenName, Mary]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mary
Context triple: [Mary Winsor, givenName, Mary]
  • A. Mary
    Mary is the middle name of Edith Tolkien, the wife of author J.R.R. Tolkien.
  • B. Mary
    Mary is the given name of Mary Catherine Bateson, an American cultural anthropologist and writer known for her work on learning and the human life cycle.
  • C. Mary
    Mary is the birth name of American actress, comedian, and writer Lily Tomlin, known for her groundbreaking work in television, film, and theater.
  • D. Mary
    Mary is a film featuring Italian actor Marco Leonardi, known for his roles in internationally acclaimed cinema.
  • E. Mary
    Mary is the first name of Tipper Gore, the American social issues advocate and former Second Lady of the United States.
  • 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 Winsor, givenName, Mary]
Generated description
Mary is a feminine given name of Hebrew origin, traditionally interpreted to mean "beloved" or "bitter," and has been widely used across cultures and centuries.
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, traditionally interpreted to mean "beloved" or "bitter," and has been widely used across cultures and centuries.
  • 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 Wollstonecraft, the pioneering 18th-century English writer and advocate of women's rights.
  • C. Mary
    Mary is the given name of Mary J. Blige, the acclaimed American singer, songwriter, and actress often called the "Queen of Hip-Hop Soul."
  • D. Mary
    Mary is the given name of Mary Sidney, an English Renaissance noblewoman, writer, and literary patron.
  • E. Mary
    Mary is the given name of Mary Cassatt, the renowned American Impressionist painter known for her depictions of women and children.
  • 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_69d86daf32ec8190a8c0466c8f49c3c0 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1837b048881908326739bbede756f completed April 17, 2026, 12:48 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffe47ef6648190bf1fe216e78ef660 completed May 10, 2026, 1:50 a.m.
NEDg Description generation batch_69ffe5a4edfc8190831ddf8a4601764e completed May 10, 2026, 1:55 a.m.
NED2 Entity disambiguation (via description) batch_69ffe687c204819092a4a8de0b9d624d completed May 10, 2026, 1:59 a.m.
Created at: April 10, 2026, 4:57 a.m.