Triple

T8892463
Position Surface form Disambiguated ID Type / Status
Subject North Wessex Downs E211711 entity
Predicate near P350 FINISHED
Object Andover E182020 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: Andover | Statement: [North Wessex Downs, near, Andover]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Andover
Context triple: [North Wessex Downs, near, Andover]
  • A. Andover chosen
    Andover is a town in Hampshire, England, known in part for its role as a major administrative and logistical center for the British Army.
  • B. Andover
    Andover is a town in northeastern Massachusetts known for its historic New England character, strong public schools, and institutions like Phillips Academy.
  • C. Andover
    Andover is a small rural town in northeastern Connecticut known for its lakes, forests, and residential character.
  • D. Andover, Maine
    Andover, Maine is a small rural town in Oxford County known for its scenic western Maine mountains, outdoor recreation, and historic New England character.
  • E. North Andover
    North Andover is a suburban town in northeastern Massachusetts known for its residential character, historic sites, and proximity to the city of Lawrence.
  • 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_69ca83907954819096d52a245b635841 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc61bb46c881909e579bb1926e5204 completed April 1, 2026, 12:07 a.m.
NED1 Entity disambiguation (via context triple) batch_69dbb6bb34548190aac9d2af05477750 completed April 12, 2026, 3:14 p.m.
Created at: March 30, 2026, 6:54 p.m.