Triple

T8910042
Position Surface form Disambiguated ID Type / Status
Subject mainland Kent E212157 entity
Predicate containsRiver P165 FINISHED
Object River Darent E78586 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 Darent | Statement: [mainland Kent, containsRiver, River Darent]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: River Darent
Context triple: [mainland Kent, containsRiver, River Darent]
  • A. River Darent chosen
    River Darent is a chalk stream river in Kent, England, flowing north through the Darent Valley to join the River Thames.
  • B. River Chelmer
    The River Chelmer is a river in Essex, England, that flows through the city of Chelmsford before joining the River Blackwater near Maldon.
  • C. River Rother
    The River Rother is a river in central England that flows through Derbyshire and South Yorkshire before joining the River Don.
  • D. River Rother
    River Rother is a river in East Sussex, England, that flows through the Weald to the English Channel near the town of Rye.
  • E. River Hamble
    The River Hamble is a river in Hampshire, England, renowned as a major yachting and boating centre and for its scenic, wooded estuary.
  • 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_69ca839255248190b43984294abd92ae completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc65227d008190b13ba162d0b3c9d1 completed April 1, 2026, 12:21 a.m.
NED1 Entity disambiguation (via context triple) batch_69d1e3d6191c8190adb41feec1bfa76e completed April 5, 2026, 4:23 a.m.
Created at: March 30, 2026, 6:55 p.m.