Triple

T20411771
Position Surface form Disambiguated ID Type / Status
Subject Avon E500602 entity
Predicate containedTown P847 FINISHED
Object Frome 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: Frome | Statement: [Avon, containedTown, Frome]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Frome
Context triple: [Avon, containedTown, Frome]
  • A. Frome chosen
    Frome is a historic market town in Somerset, England, known for its well-preserved architecture, independent shops, and vibrant arts and cultural scene.
  • B. Frome
    Frome is an electoral district in the South Australian House of Assembly, covering a largely rural region in the state's mid-north.
  • C. Bantry
    Bantry is a coastal town in southwest Ireland known for its scenic Bantry Bay, maritime heritage, and proximity to the rugged landscapes of West Cork.
  • D. Kenmare
    Kenmare is a picturesque town in southwestern Ireland known for its scenic location between the Ring of Kerry and the Beara Peninsula, attracting visitors with its natural beauty and traditional charm.
  • E. Granard
    Granard is a small market town in north County Longford, Ireland, known for its historic motte-and-bailey fort and rural surroundings.
  • 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_69e0b4a935588190b9446a99b37ced44 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e67a3f8fdc8190b05b6c41b38f34b7 completed April 20, 2026, 7:10 p.m.
Created at: April 16, 2026, 11:30 a.m.