Triple

T22367344
Position Surface form Disambiguated ID Type / Status
Subject Billingborough E552940 entity
Predicate near P350 FINISHED
Object Pointon 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: Pointon | Statement: [Billingborough, near, Pointon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pointon
Context triple: [Billingborough, near, Pointon]
  • A. Pointon chosen
    Pointon is a small village and civil parish located in the South Kesteven district of Lincolnshire, England.
  • B. New Point
    New Point is a small unincorporated community located in the U.S. state of Missouri.
  • C. Ardalanish Point
    Ardalanish Point is a scenic coastal headland on the Ross of Mull in Scotland, known for its rugged shoreline, sandy beaches, and views over the surrounding Hebridean seascape.
  • D. Quarry Point
    Quarry Point is a coastal area on Angel Island in San Francisco Bay, known for its historic quarrying activity and scenic waterfront views.
  • E. South Point
    South Point is a well-known surf break near Gracetown in Western Australia, popular for its consistent waves and scenic coastal setting.
  • 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_69e11e4affcc8190ba7c27d29062558d completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f158017400819094ebf7f91c26a724 completed April 29, 2026, 12:59 a.m.
Created at: April 16, 2026, 8:44 p.m.