Triple

T11986800
Position Surface form Disambiguated ID Type / Status
Subject 8th Engineer Regiment E285299 entity
Predicate garrison P75 FINISHED
Object Sydney E8462 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: Sydney | Statement: [8th Engineer Regiment, garrison, Sydney]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sydney
Context triple: [8th Engineer Regiment, garrison, Sydney]
  • A. Sydney
    Sydney is a recurring character in Alison Bechdel’s long-running comic strip "Dykes to Watch Out For," known for her sharp intellect and complex personal relationships within its ensemble cast.
  • B. Sydney chosen
    Sydney is Australia's largest and most populous city, renowned for its iconic harbour, Opera House, and Harbour Bridge.
  • C. Sydney
    Sydney is the spirited, fashionable young woman who serves as the central heroine of Louisa May Alcott’s novel "An Old-Fashioned Girl."
  • D. Sydney
    Sydney is a unisex given name of Old English origin meaning "wide island" that is used in various English-speaking countries.
  • E. Sydney
    Sydney is a character in the British period drama series "Lark Rise to Candleford," which portrays life in two contrasting rural communities in late 19th-century England.
  • 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_69d6ab44a77c8190a652f4b27164e4ef completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d903ae28708190a826bad1624343eb completed April 10, 2026, 2:05 p.m.
NED1 Entity disambiguation (via context triple) batch_69f60a5b024c81909e4ccfd7dec7edb3 completed May 2, 2026, 2:29 p.m.
Created at: April 8, 2026, 9:46 p.m.