Triple

T8465005
Position Surface form Disambiguated ID Type / Status
Subject Chris O'Donnell E200137 entity
Predicate spouse P13 FINISHED
Object Caroline Fentress
Caroline Fentress is an American schoolteacher best known as the wife of actor Chris O'Donnell.
E756574 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: Caroline Fentress | Statement: [Chris O'Donnell, spouse, Caroline Fentress]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Caroline Fentress
Context triple: [Chris O'Donnell, spouse, Caroline Fentress]
  • A. Caroline Ford
    Caroline Ford is a British actress best known for her role in the fantasy television series "Carnival Row."
  • B. Caroline Blakiston
    Caroline Blakiston is a British actress known for her work in film and television, including roles in productions such as the Star Wars franchise and various British dramas.
  • C. Caroline Pitts
    Caroline Pitts was the wife of U.S. Supreme Court Justice Henry Billings Brown.
  • D. Caroline Blackwood
    Caroline Blackwood was a British writer and heiress known for her darkly comic novels and memoirs, as well as her connections to the Bloomsbury and literary circles of the mid-20th century.
  • E. Amy Ferson
    Amy Ferson is an American journalist and commentator best known as the first wife of television personality and news anchor T. J. Holmes.
  • 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: Caroline Fentress
Triple: [Chris O'Donnell, spouse, Caroline Fentress]
Generated description
Caroline Fentress is an American schoolteacher best known as the wife of actor Chris O'Donnell.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Caroline Fentress
Target entity description: Caroline Fentress is an American schoolteacher best known as the wife of actor Chris O'Donnell.
  • A. Caroline Ford
    Caroline Ford is a British actress best known for her role in the fantasy television series "Carnival Row."
  • B. Caroline Blakiston
    Caroline Blakiston is a British actress known for her work in film and television, including roles in productions such as the Star Wars franchise and various British dramas.
  • C. Caroline Pitts
    Caroline Pitts was the wife of U.S. Supreme Court Justice Henry Billings Brown.
  • D. Caroline Blackwood
    Caroline Blackwood was a British writer and heiress known for her darkly comic novels and memoirs, as well as her connections to the Bloomsbury and literary circles of the mid-20th century.
  • E. Amy Ferson
    Amy Ferson is an American journalist and commentator best known as the first wife of television personality and news anchor T. J. Holmes.
  • 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_69ca83198c4c8190a337bf717d1813f5 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe4d05b2881909bddf58df0ee1143 completed March 31, 2026, 3:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69cf512d294c8190bed7e37991d237c1 completed April 3, 2026, 5:33 a.m.
NEDg Description generation batch_69cf540bee8081908f9c176a1971742f completed April 3, 2026, 5:45 a.m.
NED2 Entity disambiguation (via description) batch_69cf54a056408190bd536f79e3ec33be completed April 3, 2026, 5:48 a.m.
Created at: March 30, 2026, 6:11 p.m.