Triple

T21925214
Position Surface form Disambiguated ID Type / Status
Subject Evergreen campus E541425 entity
Predicate name P16 FINISHED
Object Evergreen campus 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: Evergreen campus | Statement: [Evergreen campus, name, Evergreen campus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Evergreen campus
Context triple: [Evergreen campus, name, Evergreen campus]
  • A. Evergreen campus chosen
    Evergreen campus is the historic, tree-lined main campus of Loyola University Maryland located in Baltimore.
  • B. Emerald Bower campus
    Emerald Bower campus is the main urban campus of Rabindra Bharati University in Kolkata, known for its focus on arts, culture, and humanities education.
  • C. Boldrewood Campus
    Boldrewood Campus is a University of Southampton site known for its focus on engineering, maritime, and industry collaboration facilities.
  • D. Evergreen Academy
    Evergreen Academy was an educational institution attended by William B. Travis, a 19th-century American lawyer and commander at the Battle of the Alamo.
  • E. Alta Vista campus
    Alta Vista campus is the University of Ottawa’s health sciences hub, housing the Faculty of Medicine and affiliated clinical and research facilities in Ottawa’s Alta Vista area.
  • 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_69e0c47d74488190a15119108794a307 completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f123fa40c48190b80a85e562ea2591 completed April 28, 2026, 9:17 p.m.
Created at: April 16, 2026, 7:46 p.m.