Triple

T22639149
Position Surface form Disambiguated ID Type / Status
Subject Colbert County, Alabama E558771 entity
Predicate hasHistoricSite P1098 FINISHED
Object Ivy Green 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: Ivy Green | Statement: [Colbert County, Alabama, hasHistoricSite, Ivy Green]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ivy Green
Context triple: [Colbert County, Alabama, hasHistoricSite, Ivy Green]
  • A. Ivy Green chosen
    Ivy Green is the historic childhood home of Helen Keller, now preserved as a museum in Tuscumbia, Alabama.
  • B. Jubilee Green
    Jubilee Green is a public park and green space in the town of Bradley Stoke, England, used for recreation and community activities.
  • C. Goose Green
    Goose Green is a settlement on East Falkland in the Falkland Islands, best known as the site of a major land battle during the 1982 Falklands War.
  • D. Goose Green
    Goose Green is a small public park and open green space in the East Dulwich area of south London, popular for recreation and community events.
  • E. Udny Green
    Udny Green is a small rural village in Aberdeenshire, Scotland, known for its traditional village green and historic parish church.
  • 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_69e24547f7fc819086e2c4ba3b979657 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f1700f9fac8190b82190a54be22413 completed April 29, 2026, 2:42 a.m.
Created at: April 17, 2026, 3:04 p.m.