Triple

T19556528
Position Surface form Disambiguated ID Type / Status
Subject Thorne E489326 entity
Predicate partOf P40 FINISHED
Object Humberhead Levels NE NERFINISHED

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: Humberhead Levels | Statement: [Thorne, partOf, Humberhead Levels]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Humberhead Levels
Context triple: [Thorne, partOf, Humberhead Levels]
  • A. Humberhead Levels chosen
    Humberhead Levels is a low-lying, largely rural wetland and agricultural landscape in northern England, characterized by its extensive river floodplains and drained peat fens.
  • B. Maesbury Marsh
    Maesbury Marsh is a small rural settlement in Shropshire, England, known for its tranquil countryside setting and proximity to the historic Montgomery Canal.
  • C. Ditton Marsh
    Ditton Marsh was the original name of what is now Esher railway station in Surrey, England, serving the local Ditton area.
  • D. Coe Fen
    Coe Fen is a riverside meadow and green space in Cambridge, England, known for its grazing cattle, footpaths, and views of historic college buildings.
  • E. Halvergate Marshes
    Halvergate Marshes is an extensive area of low-lying grazing marsh and drainage ditches in the Norfolk Broads of eastern England, noted for its wildlife and traditional wetland landscape.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8e8dc5d8c8190a6d7bd8864f43ca0 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e63d341d708190b8ef35822f8bfe7c completed April 20, 2026, 2:50 p.m.
Created at: April 10, 2026, 1:42 p.m.