Triple

T150389
Position Surface form Disambiguated ID Type / Status
Subject Bob Dylan E3416 entity
Predicate spouse P13 FINISHED
Object Carolyn Dennis
Carolyn Dennis is an American singer and backing vocalist best known for her work with Bob Dylan and for being his former wife.
E32742 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: Carolyn Dennis | Statement: [Bob Dylan, spouse, Carolyn Dennis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Carolyn Dennis
Context triple: [Bob Dylan, spouse, Carolyn Dennis]
  • A. Patricia Spence
    Patricia Spence was the second wife of British philosopher and Nobel laureate Bertrand Russell.
  • B. Ann Sadler
    Ann Sadler was the wife of John Harvard, the English clergyman and benefactor after whom Harvard University is named.
  • C. Barbara Dickson
    Barbara Dickson is a Scottish singer and actress known for her folk-inspired pop music and roles in musical theatre, including the hit musical "Blood Brothers."
  • D. Maria Skerrett
    Maria Skerrett was the second wife of British statesman Sir Robert Walpole, serving as his companion during his later years as de facto first Prime Minister of Great Britain.
  • E. Rosemary Leith
    Rosemary Leith is a Canadian-born entrepreneur and internet governance leader who co-founded the World Wide Web Foundation and serves on various boards related to technology and public policy.
  • 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: Carolyn Dennis
Triple: [Bob Dylan, spouse, Carolyn Dennis]
Generated description
Carolyn Dennis is an American singer and backing vocalist best known for her work with Bob Dylan and for being his former wife.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Carolyn Dennis
Target entity description: Carolyn Dennis is an American singer and backing vocalist best known for her work with Bob Dylan and for being his former wife.
  • A. Patricia Spence
    Patricia Spence was the second wife of British philosopher and Nobel laureate Bertrand Russell.
  • B. Ann Sadler
    Ann Sadler was the wife of John Harvard, the English clergyman and benefactor after whom Harvard University is named.
  • C. Barbara Dickson
    Barbara Dickson is a Scottish singer and actress known for her folk-inspired pop music and roles in musical theatre, including the hit musical "Blood Brothers."
  • D. Maria Skerrett
    Maria Skerrett was the second wife of British statesman Sir Robert Walpole, serving as his companion during his later years as de facto first Prime Minister of Great Britain.
  • E. Rosemary Leith
    Rosemary Leith is a Canadian-born entrepreneur and internet governance leader who co-founded the World Wide Web Foundation and serves on various boards related to technology and public policy.
  • 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_69a252868de4819080e21c9938bfe8b6 completed Feb. 28, 2026, 2:27 a.m.
NER Named-entity recognition batch_69a2580dda148190a522e0ac276d5f33 completed Feb. 28, 2026, 2:50 a.m.
NED1 Entity disambiguation (via context triple) batch_69a37656c324819099761a1d5ae00637 completed Feb. 28, 2026, 11:12 p.m.
NEDg Description generation batch_69a376c686048190aec0abd9c6999663 completed Feb. 28, 2026, 11:14 p.m.
NED2 Entity disambiguation (via description) batch_69a377aa34cc81908820a5c970d1ecf6 completed Feb. 28, 2026, 11:18 p.m.
Created at: Feb. 28, 2026, 2:31 a.m.