Triple

T22802451
Position Surface form Disambiguated ID Type / Status
Subject Sword of Lancelot E564433 entity
Predicate starring P1507 FINISHED
Object George Baker 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: George Baker | Statement: [Sword of Lancelot, starring, George Baker]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: George Baker
Context triple: [Sword of Lancelot, starring, George Baker]
  • A. George Baker chosen
    George Baker is a name shared by several notable individuals, including actors, musicians, and public figures across different English-speaking countries.
  • B. William Baker
    William Baker was a historical figure after whom London's famous Baker Street was named, likely a local landowner or developer associated with the area's early history.
  • C. William Baker
    William Baker was a 19th-century British civil engineer noted for designing major railway structures, including prominent bridges for the expanding Victorian rail network.
  • D. William Baker
    William Baker is the real name of the Marvel Comics supervillain Sandman, a frequent adversary of Spider-Man known for his sand-based shapeshifting abilities.
  • E. John Baker
    John Baker is a Canadian entrepreneur best known as the founder and longtime leader of Desire2Learn (D2L), a major provider of learning management systems and educational technology.
  • 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_69e245823f4c8190ade442cdcc2c224a completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17cdf1e308190a05d0f61856be544 completed April 29, 2026, 3:37 a.m.
Created at: April 17, 2026, 3:31 p.m.