Triple

T23384217
Position Surface form Disambiguated ID Type / Status
Subject Cranbrook Educational Community E593831 entity
Predicate architect P184 FINISHED
Object Gunnar Birkerts 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: Gunnar Birkerts | Statement: [Cranbrook Educational Community, architect, Gunnar Birkerts]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gunnar Birkerts
Context triple: [Cranbrook Educational Community, architect, Gunnar Birkerts]
  • A. Gunnar Birkerts chosen
    Gunnar Birkerts was a Latvian-American modernist architect renowned for his innovative, sculptural designs for cultural and institutional buildings in the United States.
  • B. Sven Birkerts
    Sven Birkerts is an American essayist and literary critic best known for his reflections on reading, literature, and the impact of digital technology on culture.
  • C. Nicholas Carr
    Nicholas Carr is an American writer and technology critic best known for his influential essays and books on how the internet and digital media affect cognition, culture, and work.
  • D. Kenneth Hayles
    Kenneth Hayles was a screenwriter known for his work on mid-20th-century British crime and drama films.
  • E. Bob Meyrowitz
    Bob Meyrowitz is an American media executive best known for creating and launching the Ultimate Fighting Championship (UFC), which helped popularize modern mixed martial arts.
  • 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_69e25d2754fc819085deea939bde60ab completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f1a496ae34819090e86c89eef6d2dc completed April 29, 2026, 6:26 a.m.
Created at: April 17, 2026, 5:34 p.m.