Triple

T4989849
Position Surface form Disambiguated ID Type / Status
Subject Mary Elizabeth Townshend E112102 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 royal 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 Elizabeth Townshend, givenName, Mary]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mary
Context triple: [Mary Elizabeth Townshend, givenName, Mary]
  • A. Mary
    Mary is a fictional character in B.F. Skinner’s utopian novel "Walden Two," representing one of the community’s young members shaped by its behaviorist social principles.
  • B. Mary
    Mary is the birth name of American actress, singer, and dancer Debbie Reynolds, a major Hollywood star of the mid-20th century.
  • C. Mary
    Mary is the middle name of Katherine Mary Dewar, a component of her full personal name.
  • D. 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."
  • E. Mary
    Mary is a minor character in Mark Twain's novel "The Adventures of Tom Sawyer," known as Tom's kind and well-behaved cousin.
  • 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 Elizabeth Townshend, 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 royal 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 royal 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 a central figure in Christianity, venerated as the mother of Jesus and often honored as the Virgin Mary.
  • C. Mary
    Mary is the given name of Mary Wollstonecraft, the pioneering 18th-century English writer and advocate of women's rights.
  • D. 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."
  • 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_69bd441be7bc8190b530362d427b97d2 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd727fe55881909d42e41b832b9ece completed March 20, 2026, 4:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69be8a0ac8d48190b9d050e26b67a794 completed March 21, 2026, 12:07 p.m.
NEDg Description generation batch_69be8d747c40819098ac5d475d60ab46 completed March 21, 2026, 12:22 p.m.
NED2 Entity disambiguation (via description) batch_69be8df7ab9c8190b1af6e32f0f33b30 completed March 21, 2026, 12:24 p.m.
Created at: March 20, 2026, 1:34 p.m.