Triple

T14365563
Position Surface form Disambiguated ID Type / Status
Subject Madge Sinclair E356223 entity
Predicate portrayed P1668 FINISHED
Object Belle in Roots
Belle in Roots is a compassionate and resilient enslaved woman who serves as a maternal figure and emotional anchor within the family at the heart of the miniseries.
 E1095061 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: Belle in Roots | Statement: [Madge Sinclair, portrayed, Belle in Roots]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Belle in Roots
Context triple: [Madge Sinclair, portrayed, Belle in Roots]
  • A. Belle
    Belle is the official mascot character representing Bennett College and its community spirit.
  • B. Belle
    Belle is the intelligent, book-loving heroine of Disney’s "Beauty and the Beast," known for her compassion, independence, and iconic yellow ball gown.
  • C. Belle
    Belle is a supporting character in the 2018 heist thriller film "Widows," involved in the criminal plot led by a group of women in Chicago.
  • D. Belle
    Belle Roosevelt was an American socialite and member of the prominent Roosevelt family in the late 19th and early 20th centuries.
  • E. Belle
    Belle is the given name of Belle W. Baruch, an American philanthropist, conservationist, and heiress to the Baruch family fortune.
  • 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: Belle in Roots
Triple: [Madge Sinclair, portrayed, Belle in Roots]
Generated description
Belle in Roots is a compassionate and resilient enslaved woman who serves as a maternal figure and emotional anchor within the family at the heart of the miniseries.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Belle in Roots
Target entity description: Belle in Roots is a compassionate and resilient enslaved woman who serves as a maternal figure and emotional anchor within the family at the heart of the miniseries.
  • A. Belle
    Belle is a supporting character in the 2018 heist thriller film "Widows," involved in the criminal plot led by a group of women in Chicago.
  • B. Belle
    Belle is the official mascot character representing Bennett College and its community spirit.
  • C. Belle
    Belle is the intelligent, book-loving heroine of Disney’s "Beauty and the Beast," known for her compassion, independence, and iconic yellow ball gown.
  • D. Belle
    Belle Roosevelt was an American socialite and member of the prominent Roosevelt family in the late 19th and early 20th centuries.
  • E. Belle
    Belle is the given name of Belle W. Baruch, an American philanthropist, conservationist, and heiress to the Baruch family fortune.
  • 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_69d8279163a081908aec45c0e3f1e02f completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de8fad48748190a0f34ca4d02f9a3c completed April 14, 2026, 7:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd4c4fa3788190b7fa5c34620c3ada completed May 8, 2026, 2:37 a.m.
NEDg Description generation batch_69fd4e14f4dc8190860bd3bd4e306e28 completed May 8, 2026, 2:44 a.m.
NED2 Entity disambiguation (via description) batch_69fd4ea9fefc8190a5650f8ee270f37f completed May 8, 2026, 2:47 a.m.
Created at: April 10, 2026, 1:15 a.m.