Triple

T20729064
Position Surface form Disambiguated ID Type / Status
Subject New South Wales Legislative Assembly E509518 entity
Predicate abbreviation P43 FINISHED
Object NSW LA — 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: NSW LA | Statement: [New South Wales Legislative Assembly, abbreviation, NSW LA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: NSW LA
Context triple: [New South Wales Legislative Assembly, abbreviation, NSW LA]
  • A. LA (NSW) chosen
    LA (NSW) is the standard abbreviation for the New South Wales Legislative Assembly, the lower house of the Parliament of New South Wales in Australia.
  • B. SLNSW
    SLNSW is the State Library of New South Wales, a major public research and reference library in Sydney, Australia.
  • C. AGNSW
    AGNSW is a major public art museum in Sydney, Australia, renowned for its collections of Australian, Aboriginal, European, and Asian art.
  • D. TfNSW
    TfNSW is the New South Wales government agency responsible for planning, managing, and coordinating the state’s transport systems and services.
  • E. FRNSW
    FRNSW is the primary urban fire and rescue service for the Australian state of New South Wales, responsible for firefighting, emergency response, and community safety.
  • 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_69e0b4c4cc648190b45fda6e2b20af56 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c1eb5d44819082d9fa410e676d91 completed April 21, 2026, 12:16 a.m.
Created at: April 16, 2026, 12:30 p.m.