Triple

T2392415
Position Surface form Disambiguated ID Type / Status
Subject Ray Charles E48972 entity
Predicate familyName P18 FINISHED
Object Robinson E75069 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: Robinson | Statement: [Ray Charles, familyName, Robinson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Robinson
Context triple: [Ray Charles, familyName, Robinson]
  • A. Robinson chosen
    Robinson is a common English surname borne by numerous notable figures across politics, sports, arts, and other fields.
  • B. Alexander Selkirk
    Alexander Selkirk was a Scottish sailor famously marooned on a Pacific island in the early 18th century, whose real-life survival story helped inspire Daniel Defoe’s novel "Robinson Crusoe."
  • C. James Crabe
    James Crabe was an American cinematographer best known for his work on influential films of the 1970s and 1980s, including the original Rocky.
  • D. Marlow
    Marlow is a historic English town on the River Thames in Buckinghamshire, known for its picturesque setting, suspension bridge, and literary associations.
  • E. Richard Parker
    Richard Parker is the Bengal tiger who becomes the central animal companion and symbolic figure in Yann Martel’s novel *Life of Pi*.
  • 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_69a88aa5f63081908d07fd302029fcbd completed March 4, 2026, 7:40 p.m.
NER Named-entity recognition batch_69abc87587708190a7f2bc473a898bc2 completed March 7, 2026, 6:40 a.m.
NED1 Entity disambiguation (via context triple) batch_69aeb3d7b4908190a87dd33316d2d725 completed March 9, 2026, 11:49 a.m.
Created at: March 4, 2026, 7:57 p.m.