Triple

T5631201
Position Surface form Disambiguated ID Type / Status
Subject Suncorp Group E147834 entity
Predicate hasBrand P1500 FINISHED
Object Shannons E534953 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: Shannons | Statement: [Suncorp Group, hasBrand, Shannons]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Shannons
Context triple: [Suncorp Group, hasBrand, Shannons]
  • A. Shannons chosen
    Shannons is an Australian insurance company best known for providing specialist car and motorcycle insurance, particularly for motoring enthusiasts and classic vehicle owners.
  • B. Shannon
    Shannon is a common Irish surname that originates from the River Shannon and is borne by numerous notable individuals, including mathematician and information theorist Claude Shannon.
  • C. Shannon
    Shannon is a small rural town in the Manawatū-Whanganui region of New Zealand’s North Island.
  • D. Tomlinson
    Tomlinson is a surname most notably associated with Ray Tomlinson, the American computer programmer credited with inventing networked email and introducing the "@" symbol in email addresses.
  • E. Sibert
    Sibert is the given middle name of the renowned American novelist Willa Cather, known for her depictions of frontier life on the Great Plains.
  • 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_69c00907bc8881909ed760d3ed73ef35 completed March 22, 2026, 3:21 p.m.
NER Named-entity recognition batch_69c0225cdcdc819095034f12c39ef755 completed March 22, 2026, 5:09 p.m.
NED1 Entity disambiguation (via context triple) batch_69c05a12b5bc8190a300a53a6423e81c completed March 22, 2026, 9:07 p.m.
Created at: March 22, 2026, 3:40 p.m.