Triple

T8153939
Position Surface form Disambiguated ID Type / Status
Subject Tim Lake E190396 entity
Predicate spouse P13 FINISHED
Object Mary
Mary is a central character in the romantic comedy film "About Time," known as Tim Lake's love interest and later wife.
 E222863 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: [Tim Lake, spouse, Mary]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mary
Context triple: [Tim Lake, spouse, 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: [Tim Lake, spouse, Mary]
Generated description
Mary is a central character in the romantic comedy film "About Time," known as Tim Lake's love interest and later wife.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mary
Target entity description: Mary is a central character in the romantic comedy film "About Time," known as Tim Lake's love interest and later wife.
  • A. Mary chosen
    Mary is a central character in the romantic comedy film "About Time," known for her warm, quirky personality and her relationship with the time-traveling protagonist.
  • B. Mary
    Mary is a fictional character portrayed by British actress Gemma Jones, known for her nuanced performances in film and television.
  • C. Mary
    Mary is the given name of American character actress Marjorie Main, known for her roles in classic Hollywood films.
  • D. Mary
    Mary is a central character in W. H. Auden’s long poem "For the Time Being," which reimagines the Nativity story in a modern, philosophical context.
  • E. Mary
    Mary (Polly) Prince is a fictional character best known as the free-spirited, adventurous love interest played by Jennifer Aniston in the romantic comedy film "Along Came Polly."
  • 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_69ca82bfeb6481909d07b91b5cf69f59 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb44d566b08190a6bb672f9c368806 completed March 31, 2026, 3:51 a.m.
NED1 Entity disambiguation (via context triple) batch_69cd346391fc8190a3cb45e59d9dcfcd completed April 1, 2026, 3:06 p.m.
NEDg Description generation batch_69cd37e96d7c8190b486d3e33a7f4f82 completed April 1, 2026, 3:21 p.m.
NED2 Entity disambiguation (via description) batch_69cd4e9d362481908283d58b03c7ef9b completed April 1, 2026, 4:58 p.m.
Created at: March 30, 2026, 5:37 p.m.