Triple

T12539237
Position Surface form Disambiguated ID Type / Status
Subject Constable Country E299793 entity
Predicate contains P35 FINISHED
Object Flatford E324515 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: Flatford | Statement: [Constable Country, contains, Flatford]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Flatford
Context triple: [Constable Country, contains, Flatford]
  • A. Flatford chosen
    Flatford is a small hamlet in Suffolk, England, best known for its picturesque countryside scenes immortalized in the paintings of John Constable.
  • B. Yalding
    Yalding is a historic rural village in Kent, England, known for its traditional architecture and location near the confluence of several rivers.
  • C. Paddock Wood
    Paddock Wood is a small town in Kent, England, known for its agricultural history and role as a local transport and commercial hub.
  • D. Hildenborough
    Hildenborough is a village in Kent, England, situated near Tonbridge and known for its commuter links to London and surrounding towns.
  • E. Wivenhoe
    Wivenhoe is a locality in Queensland, Australia, situated near the Wivenhoe Dam and associated with the broader Sunshine Coast region.
  • 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_69d6ada707008190aaec1238117c9379 completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d9546ebf508190ae54857e4289c6e4 completed April 10, 2026, 7:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6557cb180819083ee10708320199e completed May 2, 2026, 7:50 p.m.
Created at: April 8, 2026, 9:57 p.m.