Triple

T8948424
Position Surface form Disambiguated ID Type / Status
Subject Robert Knox E213282 entity
Predicate name P16 FINISHED
Object Robert Knox E213282 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: Robert Knox | Statement: [Robert Knox, name, Robert Knox]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Robert Knox
Context triple: [Robert Knox, name, Robert Knox]
  • A. Robert Knox chosen
    Robert Knox was a 17th-century English sailor and writer best known for his detailed account of being held captive for nearly 20 years in Ceylon (modern Sri Lanka).
  • B. Rob Knox
    Rob Knox is an American record producer and songwriter known for his work with major pop and R&B artists such as Justin Timberlake.
  • C. John Brodie
    John Brodie was a British civil engineer best known for his major infrastructure projects in Liverpool, including pioneering road tunnels and urban planning innovations.
  • D. John Brodie
    John Brodie is a former San Francisco 49ers quarterback who became a prominent American football television commentator.
  • E. John K. Knox
    John K. Knox is a notable individual distinguished enough to be specifically recognized as a prominent bearer of the surname Knox.
  • 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_69ca839843408190a39069a029a89f15 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc6709c7a48190ab503083a1d6a29f completed April 1, 2026, 12:30 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfc93c678c81909d2ab68308d7c2f0 completed April 3, 2026, 2:05 p.m.
Created at: March 30, 2026, 6:59 p.m.