Triple

T5123987
Position Surface form Disambiguated ID Type / Status
Subject Anne, Princess Royal E115539 entity
Predicate child P120 FINISHED
Object Peter Phillips E107496 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: Peter Phillips | Statement: [Anne, Princess Royal, child, Peter Phillips]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Peter Phillips
Context triple: [Anne, Princess Royal, child, Peter Phillips]
  • A. Peter Phillips chosen
    Peter Phillips is the eldest grandchild of Queen Elizabeth II and a British businessman who is the son of Anne, Princess Royal.
  • B. Prince George, Duke of Cambridge
    Prince George, Duke of Cambridge was a 19th-century British royal and senior Army officer who served as Commander-in-Chief of the British Army from 1856 to 1895.
  • C. Prince Alexander John of Wales
    Prince Alexander John of Wales was the youngest son of King Edward VII and Queen Alexandra who died shortly after birth in 1871.
  • D. Prince George
    Prince George is a city in central British Columbia, Canada, known as a regional hub for forestry, education, and transportation.
  • E. Prince George of Wales
    Prince George of Wales is the eldest son of Prince William and Catherine, Princess of Wales, and second in line to the British throne.
  • 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_69bd4442ade0819087b9461f892b206b completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd7805c55c8190bc0540d755dc6242 completed March 20, 2026, 4:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69bee06aa79481909cdd3bb5e30bc568 completed March 21, 2026, 6:16 p.m.
Created at: March 20, 2026, 1:42 p.m.