Triple

T17315396
Position Surface form Disambiguated ID Type / Status
Subject Bombo Beach E420409 entity
Predicate nearestTown P350 FINISHED
Object Kiama 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: Kiama | Statement: [Bombo Beach, nearestTown, Kiama]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kiama
Context triple: [Bombo Beach, nearestTown, Kiama]
  • A. Kiama chosen
    Kiama is a coastal town in New South Wales, Australia, known for its dramatic seaside scenery and famous blowhole.
  • B. Towradgi
    Towradgi is a coastal suburb in the northern part of Wollongong, New South Wales, known for its beach, rock pool, and relaxed residential character.
  • C. Mathoura
    Mathoura is a small rural town in the Riverina region of New South Wales, Australia, known for its timber industry, wetlands, and proximity to the Murray River.
  • D. Paringa
    Paringa is a small town in South Australia located near Renmark on the Murray River, known for its historic bridge and surrounding irrigated horticultural areas.
  • E. Warrimoo
    Warrimoo is a small residential village in the Lower Blue Mountains region of New South Wales, Australia, known for its bushland setting and commuter access to Sydney.
  • 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_69d889d22b848190a4663d0b8f8f76e7 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e4399c6ad88190ba7fcf1d2d53171c completed April 19, 2026, 2:10 a.m.
Created at: April 10, 2026, 5:43 a.m.