Triple

T14631951
Position Surface form Disambiguated ID Type / Status
Subject Dorchester E343498 entity
Predicate locatedOnRiver P165 FINISHED
Object River Frome E381451 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 Frome | Statement: [Dorchester, locatedOnRiver, River Frome]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: River Frome
Context triple: [Dorchester, locatedOnRiver, River Frome]
  • A. River Frome
    The River Frome is a river in Gloucestershire, England, that flows through the town of Stroud and the surrounding Cotswold countryside before joining the River Severn.
  • B. River Frome
    The River Frome is a river in South West England that flows through Bristol and its suburbs before joining the River Avon.
  • C. River Frome chosen
    The River Frome is a major chalk stream in Dorset, England, known for its clear waters, rich wildlife, and historic role in supporting local agriculture and settlements.
  • D. River Frome
    The River Frome is a river in Herefordshire, England, that flows through rural landscapes and market towns before joining the River Lugg.
  • E. Lez River
    The Lez River is a short coastal river in southern France that flows through the city of Montpellier before emptying into the Mediterranean Sea.
  • 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_69d822dffc3c8190aa173b90761bffda completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb4a912248190a3df7f821395c776 completed April 14, 2026, 9:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69febfcf67348190862c65faa1c815f0 completed May 9, 2026, 5:02 a.m.
Created at: April 10, 2026, 1:26 a.m.