Triple

T11192588
Position Surface form Disambiguated ID Type / Status
Subject Durack E264837 entity
Predicate includesTown P847 FINISHED
Object Karratha E257298 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: Karratha | Statement: [Durack, includesTown, Karratha]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Karratha
Context triple: [Durack, includesTown, Karratha]
  • A. Karratha chosen
    Karratha is a remote coastal city in Western Australia known for its role as a major hub for the region’s mining and liquefied natural gas industries.
  • B. Kalgoorlie
    Kalgoorlie is a historic gold-mining city in Western Australia, known for its large open-cut mines and role in the region’s mining industry.
  • C. Coolgardie
    Coolgardie is a historic gold-mining town in Western Australia that played a major role in the late 19th-century gold rush.
  • D. Mount Isa
    Mount Isa is a remote mining city in northwestern Queensland, Australia, known for one of the world’s largest underground zinc, lead, and silver mines.
  • E. Coonabarabran
    Coonabarabran is a rural town in New South Wales, Australia, known as a gateway to the Warrumbungle National Park and for its strong association with astronomy and nearby observatories.
  • 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_69d6aa9eb9248190b20211772621b4bc completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e8be025481909d311b587418dfb2 completed April 9, 2026, 5:58 p.m.
NED1 Entity disambiguation (via context triple) batch_69e55630478c8190aeee4cc219209ccb completed April 19, 2026, 10:24 p.m.
Created at: April 8, 2026, 9:29 p.m.