Triple

T21378419
Position Surface form Disambiguated ID Type / Status
Subject Lyle D. Roelofs E527274 entity
Predicate employer P7 FINISHED
Object Berea College 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: Berea College | Statement: [Lyle D. Roelofs, employer, Berea College]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Berea College
Context triple: [Lyle D. Roelofs, employer, Berea College]
  • A. Berea College chosen
    Berea College is a private liberal arts work college in Berea, Kentucky, known for offering tuition-free education to students, particularly from Appalachia and low-income backgrounds.
  • B. Belmont College
    Belmont College is a public community college serving students in and around Belmont County, Ohio, with career-focused and transfer-oriented programs.
  • C. Marietta College
    Marietta College is a private liberal arts college in Marietta, Ohio, known for its strong programs in petroleum engineering and the liberal arts.
  • D. Berea Community School
    Berea Community School is a public K–12 educational institution serving students in the town of Berea, Kentucky.
  • E. Burnside College
    Burnside College is a secondary school and sixth form serving the community of Wallsend in Tyne and Wear, England.
  • 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_69e0b51f363c8190944000ab5523b02b completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e8b0ca5e1c81909b06958459c553dc completed April 22, 2026, 11:28 a.m.
Created at: April 16, 2026, 5:11 p.m.