Triple

T4126839
Position Surface form Disambiguated ID Type / Status
Subject Inverness railway station E92745 entity
Predicate connectsTo P845 FINISHED
Object Perth E17483 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: Perth | Statement: [Inverness railway station, connectsTo, Perth]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Perth
Context triple: [Inverness railway station, connectsTo, Perth]
  • A. Perth chosen
    Perth is a historic city in central Scotland, often called the "Fair City," known for its medieval heritage and role as a former Scottish capital.
  • B. Perth
    Perth is the capital and largest city of Western Australia, known for its coastal lifestyle, sunny climate, and isolation as one of the world’s most remote major cities.
  • C. Fremantle
    Fremantle is a global television production and distribution company known for creating and producing major entertainment formats and reality shows.
  • D. Fremantle
    Fremantle is a historic port city at the mouth of the Swan River, known for its maritime heritage, preserved 19th-century architecture, and vibrant arts and café culture.
  • E. Adelaide
    Adelaide is the coastal capital city of South Australia, known for its festivals, wine regions, and planned grid layout.
  • 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_69aed9685f70819086932777aec8d959 completed March 9, 2026, 2:30 p.m.
NER Named-entity recognition batch_69af0219f0e48190b0a925f09d858d65 completed March 9, 2026, 5:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69b589c825a881908baa9014124548ff completed March 14, 2026, 4:16 p.m.
Created at: March 9, 2026, 3:42 p.m.