Triple

T4310422
Position Surface form Disambiguated ID Type / Status
Subject Maitland Gaol E94058 entity
Predicate architect P184 FINISHED
Object Mortimer Lewis E312970 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: Mortimer Lewis | Statement: [Maitland Gaol, architect, Mortimer Lewis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mortimer Lewis
Context triple: [Maitland Gaol, architect, Mortimer Lewis]
  • A. Mortimer Lewis chosen
    Mortimer Lewis was a 19th-century British-born Australian architect who served as Colonial Architect of New South Wales and designed many of Sydney’s prominent public buildings.
  • B. Humphrey Searle
    Humphrey Searle was a 20th-century British composer known for his pioneering use of serialism and his influential orchestral and film scores.
  • C. Richard Lechmere
    Richard Lechmere was a prominent landowner and political figure in colonial Massachusetts whose family name is commemorated in various local place names.
  • D. Thomas Frankland Lewis
    Thomas Frankland Lewis was a 19th-century British politician and public servant known for his work on poor law reform and parliamentary inquiries.
  • E. Arthur Lyttelton
    Arthur Lyttelton was a 19th-century English Anglican clergyman and academic who became the first Master of Selwyn College, Cambridge.
  • 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_69b3451886588190a3dd1305ea7c58dc completed March 12, 2026, 10:58 p.m.
NER Named-entity recognition batch_69b350d55d748190a57fabcf58782dba completed March 12, 2026, 11:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5c759b65081909b02db56febbc484 completed March 14, 2026, 8:38 p.m.
Created at: March 12, 2026, 11:11 p.m.