Triple

T10949566
Position Surface form Disambiguated ID Type / Status
Subject Simon Starling E258689 entity
Predicate name P16 FINISHED
Object Simon Starling E258689 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: Simon Starling | Statement: [Simon Starling, name, Simon Starling]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Simon Starling
Context triple: [Simon Starling, name, Simon Starling]
  • A. Simon Starling chosen
    Simon Starling is a British conceptual artist and Turner Prize winner known for his research-driven works that explore transformation, history, and the circulation of objects.
  • B. Martin Boyce
    Martin Boyce is a Scottish contemporary artist known for his atmospheric, sculptural installations that often reference modernist design and architecture.
  • C. Charles Ray
    Charles Ray is an American contemporary sculptor renowned for his conceptually rigorous, often unsettling works that challenge perceptions of scale, realism, and the human figure.
  • D. John Curry
    John Curry was a pioneering British figure skater and Olympic champion renowned for transforming men's figure skating with his balletic, artistic style.
  • E. Simon Raby
    Simon Raby is a New Zealand cinematographer known for his work on visually ambitious genre films, including the 2018 adaptation of "Mortal Engines."
  • 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_69d6aa88500c819097d7032ca578e74f completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d770ec7028819084f5ce2035a128e4 completed April 9, 2026, 9:27 a.m.
NED1 Entity disambiguation (via context triple) batch_69e23c4a75688190894c83b8964509a6 completed April 17, 2026, 1:57 p.m.
Created at: April 8, 2026, 9:23 p.m.