Triple

T10937972
Position Surface form Disambiguated ID Type / Status
Subject Thomas Shelby E258385 entity
Predicate child P120 FINISHED
Object Charles Shelby E895213 NE FINISHED

How this triple was built (2 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: Charles Shelby | Statement: [Thomas Shelby, child, Charles Shelby]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Charles Shelby
Context triple: [Thomas Shelby, child, Charles Shelby]
  • A. Charles Shelby chosen
    Charles Shelby is the young son of Peaky Blinders gang leader Thomas "Tommy" Shelby in the British television series Peaky Blinders.
  • B. Charles Logan
    Charles Logan is a fictional U.S. President and recurring antagonist in the television series "24," known for his corruption, cowardice, and involvement in high-level conspiracies.
  • C. James Boyd
    James Boyd was a British Loyalist officer during the American Revolutionary War, best known for leading Loyalist forces in the Battle of Kettle Creek in Georgia.
  • D. James Boyd
    James Boyd is a relatively common personal name shared by multiple individuals across various fields, including literature, sports, and public service.
  • E. Charles Lawton Jr.
    Charles Lawton Jr. was an American cinematographer known for his work on numerous Hollywood films from the 1930s through the 1950s.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d6aa8769b4819082bfe5e61b9017f0 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d770b12a9881909305db49aa554a1b completed April 9, 2026, 9:26 a.m.
NED1 Entity disambiguation (via context triple) batch_69e2d722972c8190b14637dc9e52ce11 completed April 18, 2026, 12:58 a.m.
Created at: April 8, 2026, 9:23 p.m.