Triple

T19457146
Position Surface form Disambiguated ID Type / Status
Subject Launceston E486762 entity
Predicate nearbySettlement P350 FINISHED
Object Lifton 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: Lifton | Statement: [Launceston, nearbySettlement, Lifton]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lifton
Context triple: [Launceston, nearbySettlement, Lifton]
  • A. Lifton chosen
    Lifton is a small rural village and civil parish in West Devon, England, known for its historic character and agricultural surroundings.
  • B. Harrer
    Harrer is a surname most notably associated with Austrian mountaineer and author Heinrich Harrer, known for his book "Seven Years in Tibet."
  • C. Munitz
    Munitz is a surname most notably associated with Barry Munitz, an American educator and former university and foundation executive.
  • D. Wollheim
    Wollheim is a German-origin surname associated with several notable figures in literature and publishing.
  • E. Leibowitz
    Leibowitz is the birth surname of American comedian and former "The Daily Show" host Jon Stewart.
  • 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_69d8e8d86d608190bd199a98d0297f27 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e633c4088881908f23f25a82a513f6 completed April 20, 2026, 2:10 p.m.
Created at: April 10, 2026, 1:38 p.m.