Triple

T19510428
Position Surface form Disambiguated ID Type / Status
Subject George Esson E488136 entity
Predicate name P16 FINISHED
Object George Esson NE NERFINISHED

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: George Esson | Statement: [George Esson, name, George Esson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: George Esson
Context triple: [George Esson, name, George Esson]
  • A. George Esson chosen
    George Esson is a Scottish former senior police officer known for his prominent roles in major criminal investigations and public safety operations in the UK.
  • B. C. W. Orr
    C. W. Orr was an English composer best known for his art songs, particularly his settings of A. E. Housman's poetry.
  • C. Holt Mackenzie
    Holt Mackenzie was a British colonial administrator in India known for helping design and implement early 19th-century land revenue and settlement reforms in North India.
  • D. M. C. Fyles
    M. C. Fyles was a mountaineer known for making early ascents of peaks in British Columbia, Canada.
  • E. Jules Allard
    Jules Allard was a French craftsman and entrepreneur best known for founding the prestigious interior decoration firm Jules Allard et Fils, which specialized in luxurious, historically inspired interiors for elite clients in the late 19th and early 20th centuries.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8e8da8bec819081f400199491ccc3 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e6351547e481909a875bba40651094 completed April 20, 2026, 2:15 p.m.
Created at: April 10, 2026, 1:40 p.m.