Triple

T5582147
Position Surface form Disambiguated ID Type / Status
Subject Portland Castle E146663 entity
Predicate near P350 FINISHED
Object Weymouth E184705 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: Weymouth | Statement: [Portland Castle, near, Weymouth]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Weymouth
Context triple: [Portland Castle, near, Weymouth]
  • A. Weymouth chosen
    Weymouth is a seaside town and popular tourist resort on the south coast of Dorset, England, known for its sandy beach and Georgian seafront.
  • B. Weymouth
    Weymouth is a coastal town in eastern Massachusetts known as one of the state’s oldest settlements and a residential suburb of Boston.
  • C. Devonport
    Devonport is a coastal city in northern Tasmania, Australia, known as a key regional port and gateway to the island via the Spirit of Tasmania ferry.
  • D. Devonport
    Devonport is a port city in southwest England, now part of Plymouth, historically known for its major naval dockyard and maritime heritage.
  • E. Devonport
    Devonport is a historic seaside suburb of Auckland, New Zealand, known for its naval base, Victorian architecture, and views of the city skyline and surrounding harbours.
  • 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_69c0090287a08190b4098411effe970c completed March 22, 2026, 3:21 p.m.
NER Named-entity recognition batch_69c0208333f08190bf0049b6bdd280f5 completed March 22, 2026, 5:01 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0b0918b088190b0fcd0ab02091eb2 completed March 23, 2026, 3:16 a.m.
Created at: March 22, 2026, 3:37 p.m.