Triple

T17022962
Position Surface form Disambiguated ID Type / Status
Subject SILLIAC E412989 entity
Predicate operatingOrganization P254 FINISHED
Object University of Sydney Computation Laboratory E938556 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: University of Sydney Computation Laboratory | Statement: [SILLIAC, operatingOrganization, University of Sydney Computation Laboratory]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: University of Sydney Computation Laboratory
Context triple: [SILLIAC, operatingOrganization, University of Sydney Computation Laboratory]
  • A. School of Computer Science, University of Sydney chosen
    The School of Computer Science at the University of Sydney is a leading academic department focused on research and education in computer science and related disciplines within one of Australia’s top universities.
  • B. School of Computer Science and Engineering, UNSW
    The School of Computer Science and Engineering at UNSW is a leading Australian academic unit specializing in computer science, software engineering, and related disciplines, known for its research, teaching, and industry engagement.
  • C. NICTA
    NICTA (National ICT Australia) was an Australian research centre of excellence focused on information and communications technology, known for its work in areas such as formal methods, software systems, and data analytics.
  • D. Computer Systems Research Group
    The Computer Systems Research Group was a research team at the University of California, Berkeley, best known for creating and advancing the Berkeley Software Distribution (BSD) version of Unix.
  • E. Institute of Computing
    The Institute of Computing is the computer science and information technology faculty of the University of Campinas in Brazil, known for its research and education in computing-related fields.
  • 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_69d886cc4170819093deddc7b8b4b6a7 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d5d2abbc81908943becf5f539fc6 completed April 18, 2026, 7:04 p.m.
NED1 Entity disambiguation (via context triple) batch_6a011b514de481909c78c17a3014b468 completed May 10, 2026, 11:57 p.m.
Created at: April 10, 2026, 5:33 a.m.