Triple

T14741302
Position Surface form Disambiguated ID Type / Status
Subject Somerset v Stewart E346353 entity
Predicate hasPlaintiff P15074 FINISHED
Object James Somerset
James Somerset was an enslaved African whose 1772 legal case in England, Somerset v Stewart, became a landmark decision challenging the legality of slavery in Britain.
E1116866 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: James Somerset | Statement: [Somerset v Stewart, hasPlaintiff, James Somerset]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: James Somerset
Context triple: [Somerset v Stewart, hasPlaintiff, James Somerset]
  • A. Thomas Shepherd
    Thomas Shepherd is an author known for writing the story for the film "Dolittle."
  • B. Clement Marsh
    Clement Marsh is a fictional character featured in the artwork "Girl in Landscape."
  • C. William Sandcroft
    William Sandcroft was a heraldic designer best known for creating the original coat of arms of Jamaica.
  • D. Edward Shearmur
    Edward Shearmur is a British film composer known for his orchestral scores for a wide range of Hollywood movies and television projects.
  • E. William Welsh
    William Welsh was an early 20th-century American film actor known for his numerous roles in silent-era motion pictures.
  • 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: James Somerset
Triple: [Somerset v Stewart, hasPlaintiff, James Somerset]
Generated description
James Somerset was an enslaved African whose 1772 legal case in England, Somerset v Stewart, became a landmark decision challenging the legality of slavery in Britain.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: James Somerset
Target entity description: James Somerset was an enslaved African whose 1772 legal case in England, Somerset v Stewart, became a landmark decision challenging the legality of slavery in Britain.
  • A. Thomas Shepherd
    Thomas Shepherd is an author known for writing the story for the film "Dolittle."
  • B. Clement Marsh
    Clement Marsh is a fictional character featured in the artwork "Girl in Landscape."
  • C. William Sandcroft
    William Sandcroft was a heraldic designer best known for creating the original coat of arms of Jamaica.
  • D. Edward Shearmur
    Edward Shearmur is a British film composer known for his orchestral scores for a wide range of Hollywood movies and television projects.
  • E. William Welsh
    William Welsh was an early 20th-century American film actor known for his numerous roles in silent-era motion pictures.
  • 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_69d822e6f1c88190bc494d491a907114 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69dec7345680819093e901233a064e48 completed April 14, 2026, 11:01 p.m.
NED1 Entity disambiguation (via context triple) batch_69fdfb93e94c8190beba605e26d4552c completed May 8, 2026, 3:04 p.m.
NEDg Description generation batch_69fdff025e00819089ad734f74b64f26 completed May 8, 2026, 3:19 p.m.
NED2 Entity disambiguation (via description) batch_69fdff8bdefc8190a4a66c742e1cae83 completed May 8, 2026, 3:21 p.m.
Created at: April 10, 2026, 1:30 a.m.