Triple

T8226358
Position Surface form Disambiguated ID Type / Status
Subject Classis Britannica E192181 entity
Predicate hadBase P72117 FINISHED
Object Reculver E229760 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: Reculver | Statement: [Classis Britannica, hadBase, Reculver]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Reculver
Context triple: [Classis Britannica, hadBase, Reculver]
  • A. Reculver, Kent chosen
    Reculver, Kent is a coastal village in southeast England known for its historic Roman fort, medieval church ruins, and use as a World War II weapons testing site.
  • B. Southsea Castle
    Southsea Castle is a 16th-century coastal artillery fort in Portsmouth, England, built by Henry VIII to defend the Solent and the naval base at Portsmouth.
  • C. Beaumaris
    Beaumaris is a historic seaside town in Wales best known for its impressive medieval castle and picturesque setting on the Isle of Anglesey.
  • D. Orford Castle
    Orford Castle is a well-preserved 12th-century royal fortress in Suffolk, England, notable for its unique polygonal keep and historical significance in medieval coastal defense.
  • E. Oxwich Castle
    Oxwich Castle is a 16th-century fortified manor house on the Gower Peninsula in Wales, noted for its Tudor architecture and coastal setting.
  • 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_69ca82db5b90819085d1ad7c2e27bfcc completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb77fc10f48190b7e241c89885a478 completed March 31, 2026, 7:30 a.m.
NED1 Entity disambiguation (via context triple) batch_69ccee140e708190bf07a63fecd08c7f completed April 1, 2026, 10:06 a.m.
Created at: March 30, 2026, 5:45 p.m.