Triple

T22770728
Position Surface form Disambiguated ID Type / Status
Subject Thomas Chatterton E563547 entity
Predicate apprenticedTo P7251 FINISHED
Object John Lambert NE NERFINISHED

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: John Lambert | Statement: [Thomas Chatterton, apprenticedTo, John Lambert]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Lambert
Context triple: [Thomas Chatterton, apprenticedTo, John Lambert]
  • A. John Lambert
    John Lambert was an early American politician from New Jersey who served as a U.S. Senator and Acting Governor of New Jersey in the early 19th century.
  • B. John Lambert chosen
    John Lambert was a prominent Parliamentarian general and political figure during the English Civil Wars, noted for his military skill and later role in the republican government.
  • C. John Lambert
    John Lambert was a British Army general of the Napoleonic era, noted for leading British forces in the aftermath of the failed assault at the Battle of New Orleans.
  • D. Andrew Lambert
    Andrew Lambert is a British naval historian and academic known for his work on maritime history and strategy.
  • E. Scott Lambert
    Scott Lambert is a film producer known for his work on acclaimed projects including the psychological drama "Tár."
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e24554497c819080b996e071de27c2 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17b5e77d081909ea58d55c240662c completed April 29, 2026, 3:30 a.m.
Created at: April 17, 2026, 3:27 p.m.