Triple

T8628192
Position Surface form Disambiguated ID Type / Status
Subject Sam Elliott E204331 entity
Predicate educatedAt P5 FINISHED
Object Clark College E149776 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: Clark College | Statement: [Sam Elliott, educatedAt, Clark College]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Clark College
Context triple: [Sam Elliott, educatedAt, Clark College]
  • A. Clark College
    Clark College is a public community college known for providing two-year degrees, workforce training, and transfer programs to students in the Vancouver, Washington area.
  • B. Clark College chosen
    Clark College was a historically Black liberal arts college in Atlanta, Georgia, that later became part of Clark Atlanta University through a merger.
  • C. Delta College
    Delta College is a public community college in Michigan known for serving the Great Lakes Bay Region with associate degree and certificate programs.
  • D. John Wood Community College
    John Wood Community College is a public two-year institution in Quincy, Illinois, offering associate degrees, certificates, and workforce training programs for local and regional students.
  • E. Jefferson Community College
    Jefferson Community College is a public two-year college serving the higher education and workforce training needs of the Watertown, New York region.
  • 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_69ca834a4ea0819094970dceb9e389f3 completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc472ccc0c81908e0708c94a7cbe65 completed March 31, 2026, 10:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69cebbf918f08190a9b0469eae8e0e0d completed April 2, 2026, 6:56 p.m.
Created at: March 30, 2026, 6:27 p.m.