Triple

T23050560
Position Surface form Disambiguated ID Type / Status
Subject Steve Wozniak E573998 entity
Predicate educatedAt P5 FINISHED
Object De Anza 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: De Anza College | Statement: [Steve Wozniak, educatedAt, De Anza College]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: De Anza College
Context triple: [Steve Wozniak, educatedAt, De Anza College]
  • A. De Anza College chosen
    De Anza College is a community college in Cupertino, California, known for its strong academic programs and proximity to Silicon Valley.
  • B. Cuyamaca College
    Cuyamaca College is a public community college in El Cajon, California, offering two-year degree, transfer, and career education programs.
  • C. Santa Ana College
    Santa Ana College is a public community college in Santa Ana, California, known for offering a wide range of academic and vocational programs.
  • D. Palomar College
    Palomar College is a public community college serving North San Diego County with a wide range of academic, vocational, and transfer programs.
  • E. Mt. San Antonio College
    Mt. San Antonio College is a large public community college in Walnut, California, known for its comprehensive academic and vocational programs.
  • 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_69e245b9c11481909d06c872214d21af completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1867c443081909588262bc90748af completed April 29, 2026, 4:18 a.m.
Created at: April 17, 2026, 3:54 p.m.