Triple

T5518080
Position Surface form Disambiguated ID Type / Status
Subject Mary Eunice Harlan E144734 entity
Predicate givenName P17 FINISHED
Object Mary
Mary is a common female given name with biblical origins, traditionally associated with the mother of Jesus in Christian tradition.
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 Eunice Harlan, givenName, Mary]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mary
Context triple: [Mary Eunice Harlan, givenName, Mary]
  • A. Mary
    Mary is the given name of Mary Wollstonecraft, the pioneering 18th-century English writer and advocate of women's rights.
  • B. Mary
    Mary is the given first name of the acclaimed American actress Meryl Streep.
  • C. Mary
    Mary Eleanor Darwin was a member of the Darwin family, known primarily as a descendant of the naturalist Charles Darwin.
  • D. Mary
    Mary is the middle name of Theresa May, the former Prime Minister of the United Kingdom.
  • E. Mary
    Mary is the given name of Lady Mary Palliser, a fictional aristocratic character from Anthony Trollope’s Palliser novels.
  • 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 Eunice Harlan, givenName, Mary]
Generated description
Mary is a common female given name with biblical origins, traditionally associated with the mother of Jesus in Christian tradition.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mary
Target entity description: Mary is a common female given name with biblical origins, traditionally associated with the mother of Jesus in Christian tradition.
  • 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 Cassatt, the renowned American Impressionist painter known for her depictions of women and children.
  • E. 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."
  • 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_69c008f77ff88190b0cd50ca207295d1 completed March 22, 2026, 3:21 p.m.
NER Named-entity recognition batch_69c01f6cefe48190bfda90d6afab8468 completed March 22, 2026, 4:57 p.m.
NED1 Entity disambiguation (via context triple) batch_69c027e1ed4c81908f670286556ced81 completed March 22, 2026, 5:33 p.m.
NEDg Description generation batch_69c03847b3348190be97b7c5795df368 completed March 22, 2026, 6:43 p.m.
NED2 Entity disambiguation (via description) batch_69c038e148a0819080a306307e60d437 completed March 22, 2026, 6:45 p.m.
Created at: March 22, 2026, 3:33 p.m.