Triple

T4083693
Position Surface form Disambiguated ID Type / Status
Subject Salisbury E87538 entity
Predicate locatedOnRiver P165 FINISHED
Object River Avon E136971 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: River Avon | Statement: [Salisbury, locatedOnRiver, River Avon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: River Avon
Context triple: [Salisbury, locatedOnRiver, River Avon]
  • A. River Avon
    River Avon is a river in central England best known for flowing through Stratford-upon-Avon, the birthplace of William Shakespeare.
  • B. River Avon
    The River Avon is a major river in southwest England that flows through the city of Bath and eventually joins the River Severn.
  • C. River Avon
    The River Avon is a major river in the South Island of New Zealand, known for flowing through the city of Christchurch and its surrounding regions.
  • D. River Avon chosen
    The River Avon is a major river in southern England that flows through counties including Hampshire before reaching the English Channel at Christchurch.
  • E. River Avon
    The River Avon is a Scottish river that flows through Lanarkshire and joins the River Clyde near Hamilton, contributing to the Clyde’s central lowlands drainage system.
  • 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_69aed9435cf48190ad1da737c962d19d completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aefc7933b481909bb3e02c6c04c8ee completed March 9, 2026, 4:59 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5769bafbc8190b14fb80b663b3747 completed March 14, 2026, 2:54 p.m.
Created at: March 9, 2026, 3:39 p.m.