Triple

T23092001
Position Surface form Disambiguated ID Type / Status
Subject RAF Upavon E575778 entity
Predicate locatedIn P40 FINISHED
Object Upavon 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: Upavon | Statement: [RAF Upavon, locatedIn, Upavon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Upavon
Context triple: [RAF Upavon, locatedIn, Upavon]
  • A. Upavon chosen
    Upavon is a village on Salisbury Plain in Wiltshire, England, notable for its long military association and nearby army and air force facilities.
  • B. Opherdicke
    Opherdicke is a village in North Rhine-Westphalia, Germany, known for its historic moated castle Haus Opherdicke and its rural setting within the municipality of Holzwickede.
  • C. Yorton
    Yorton is a small rural village in Shropshire, England, known for its modest railway station on the Crewe–Shrewsbury line.
  • D. Grindon
    Grindon is a residential suburb of Sunderland in the Wearside area of North East England.
  • E. Alveston
    Alveston is a village and civil parish in South Gloucestershire, England, situated near the town of Thornbury.
  • 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_69e245bf3e3c819086d3448720efc01b completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f18daa68d48190842e9cb6de31ea79 completed April 29, 2026, 4:48 a.m.
Created at: April 17, 2026, 3:57 p.m.