Triple

T2893228
Position Surface form Disambiguated ID Type / Status
Subject Vian E63875 entity
Predicate notableBearer P458 FINISHED
Object Philip Vian E10432 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: Philip Vian | Statement: [Vian, notableBearer, Philip Vian]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Philip Vian
Context triple: [Vian, notableBearer, Philip Vian]
  • A. Philip Vian chosen
    Philip Vian was a distinguished British Royal Navy admiral known for his aggressive leadership in destroyer actions and key naval engagements during the Second World War.
  • B. Eric Frank Russell
    Eric Frank Russell was a British science fiction author known for his witty, humanistic stories and influential contributions to mid-20th-century speculative fiction.
  • C. Philip May
    Philip May is a British investment manager best known as the husband of former UK Prime Minister Theresa May.
  • D. Ernest Merritt
    Ernest Merritt was an American physicist and academic who co-founded the influential scientific journal Physical Review and helped shape early 20th-century physics research in the United States.
  • E. Philip José Farmer
    Philip José Farmer was an American science fiction and fantasy author known for his imaginative world-building, boundary-pushing themes, and influential series such as the Riverworld and World of Tiers sagas.
  • 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_69ab4c45822c8190830c5f2bb97bcfd0 completed March 6, 2026, 9:51 p.m.
NER Named-entity recognition batch_69abe062234c81909411e34db7d2683d completed March 7, 2026, 8:22 a.m.
NED1 Entity disambiguation (via context triple) batch_69b031814764819096a1664b468ec817 completed March 10, 2026, 2:58 p.m.
Created at: March 6, 2026, 10:07 p.m.