Triple

T9746497
Position Surface form Disambiguated ID Type / Status
Subject Queen Mary E236322 entity
Predicate givenName P17 FINISHED
Object Mary
Mary is a female given name of Hebrew origin that has been widely used across cultures and history, notably among European royalty and 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: [Queen Mary, givenName, Mary]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mary
Context triple: [Queen Mary, 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 middle name of Theresa May, the former Prime Minister of the United Kingdom.
  • C. Mary
    Mary I of England was the 16th-century Queen of England and Ireland best known for her attempt to restore Roman Catholicism and for the Marian persecutions that earned her the nickname "Bloody Mary."
  • D. Mary
    Mary is a studio album by Ghanaian rapper Sarkodie, known for its highlife influences and tribute to his late grandmother.
  • 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: [Queen Mary, givenName, Mary]
Generated description
Mary is a female given name of Hebrew origin that has been widely used across cultures and history, notably among European royalty and in Christian tradition.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mary
Target entity description: Mary is a female given name of Hebrew origin that has been widely used across cultures and history, notably among European royalty and 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 the given name of Mary Sidney, an English Renaissance noblewoman, writer, and literary patron.
  • 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 Anne Galton, a historical figure known primarily through her familial and biographical associations.
  • E. Mary
    Mary is the given name of Lady Mary Wortley Montagu, an 18th-century English aristocrat, writer, and early advocate of smallpox inoculation.
  • 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_69ca84d3e24481908a476e2231123cf9 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cd9f65ad788190b68d731b6f516d93 completed April 1, 2026, 10:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1c40b0db081908b956484e3ff44c0 completed April 5, 2026, 2:08 a.m.
NEDg Description generation batch_69d1c7bfda588190ae5432f4c20968c7 completed April 5, 2026, 2:24 a.m.
NED2 Entity disambiguation (via description) batch_69d1c811129481909c383caae1c5969b completed April 5, 2026, 2:25 a.m.
Created at: March 30, 2026, 8:23 p.m.