Triple

T17652860
Position Surface form Disambiguated ID Type / Status
Subject Gulf Country E429537 entity
Predicate containsTown P847 FINISHED
Object Karumba 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: Karumba | Statement: [Gulf Country, containsTown, Karumba]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Karumba
Context triple: [Gulf Country, containsTown, Karumba]
  • A. Karumba chosen
    Karumba is a small coastal town and fishing port in Queensland, Australia, known for its prawn and barramundi industries and sunsets over the Gulf of Carpentaria.
  • B. Walata
    Walata is an ancient trading town in present-day Mauritania that was a key stop on trans-Saharan caravan routes and an important center of Islamic scholarship in West Africa.
  • C. Gilgandra
    Gilgandra is a rural town in New South Wales, Australia, known as a service and agricultural centre on the western plains.
  • D. Boorabbin
    Boorabbin is a sparsely populated locality in Western Australia’s Goldfields region, known for its remote bushland and proximity to the Great Eastern Highway.
  • E. Bundarra
    Bundarra is a small rural town in the New England region of New South Wales, Australia, known for its historic buildings and surrounding agricultural countryside.
  • 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_69d889e2c2608190b762e76d9b2262f1 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e46e3e0ae481908382570f802d8144 completed April 19, 2026, 5:55 a.m.
Created at: April 10, 2026, 6:05 a.m.