Triple

T14885367
Position Surface form Disambiguated ID Type / Status
Subject Turkey Tolson Tjupurrula E350106 entity
Predicate workLocation P7 FINISHED
Object Kintore E1093667 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: Kintore | Statement: [Turkey Tolson Tjupurrula, workLocation, Kintore]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kintore
Context triple: [Turkey Tolson Tjupurrula, workLocation, Kintore]
  • A. Kintore chosen
    Kintore is a remote Indigenous Australian community in the Northern Territory, known as a significant center for Western Desert art and culture.
  • B. Kinsach
    Kinsach is a small river in the Straubing-Bogen district of Bavaria, Germany.
  • C. Glen Tanar
    Glen Tanar is a scenic glen in Aberdeenshire, Scotland, known for its ancient Caledonian pine forest, wildlife, and outdoor recreation within the Cairngorms National Park.
  • D. Cregneash
    Cregneash is a traditional Manx village on the Isle of Man known for its preserved thatched cottages and open-air folk museum showcasing historic rural life.
  • E. Kinloch
    Kinloch is a small settlement on the Isle of Rùm in Scotland, serving as the island’s main village and harbour.
  • 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_69d822ee4f408190b6ac3b2fa434f0df completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69ded5f4598081908735e8d7dfce8074 completed April 15, 2026, 12:04 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe9dbf1f5c8190ad4626d14e0d8109 completed May 9, 2026, 2:36 a.m.
Created at: April 10, 2026, 1:56 a.m.