Triple

T20118849
Position Surface form Disambiguated ID Type / Status
Subject Take a Message to Mary E490541 entity
Predicate mainCharacters P9202 FINISHED
Object Mary
Mary is a fictional woman who is the recipient of a crucial message in the narrative of the song "Take a Message to Mary."
E1411140 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: [Take a Message to Mary, mainCharacters, Mary]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mary
Context triple: [Take a Message to Mary, mainCharacters, Mary]
  • A. 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.
  • B. Mary
    Mary is the middle name of Edith Tolkien, the wife of author J.R.R. Tolkien.
  • 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 the given first name of Eugenia Charles, the pioneering former Prime Minister of Dominica and one of the Caribbean’s most prominent female political leaders.
  • E. Mary
    Mary is the middle name of the renowned British archaeologist Kathleen Kenyon.
  • 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: [Take a Message to Mary, mainCharacters, Mary]
Generated description
Mary is a fictional woman who is the recipient of a crucial message in the narrative of the song "Take a Message to Mary."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mary
Target entity description: Mary is a fictional woman who is the recipient of a crucial message in the narrative of the song "Take a Message to Mary."
  • A. Mary
    Mary is a central female character in Bruce Springsteen's song "Thunder Road," symbolizing hope, escape, and the possibility of a new life.
  • B. Mary
    Mary is the central, titular figure evoked in Jimi Hendrix’s song “The Wind Cries Mary,” often interpreted as a symbol of lost love and melancholy.
  • C. Mary
    Mary is a person known primarily through her relationship with Silas, about whom limited additional context is provided.
  • D. Mary
    Mary is a central character in Ralph Vaughan Williams's opera "Hugh the Drover," serving as the romantic interest whose choices drive much of the plot.
  • E. Mary
    Mary is the given name of American actress and singer-songwriter Mare Winningham, known for her work in film, television, and music.
  • F. None of above. chosen

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_69da62636cc08190982cc71733a17b8d completed April 11, 2026, 3:01 p.m.
NER Named-entity recognition batch_69e6673c32bc8190a52875961fbcc5e2 completed April 20, 2026, 5:49 p.m.
NED1 Entity disambiguation (via context triple) batch_6a08270edd6481909230ece4487f93fd completed May 16, 2026, 8:13 a.m.
NEDg Description generation batch_6a0827c6a68c8190aed2d531b4fd2030 completed May 16, 2026, 8:16 a.m.
NED2 Entity disambiguation (via description) batch_6a08288d98fc8190a146f43a027682f0 completed May 16, 2026, 8:19 a.m.
Created at: April 11, 2026, 11:30 p.m.