Triple

T20274113
Position Surface form Disambiguated ID Type / Status
Subject Jeff Corwin E502965 entity
Predicate familyName P18 FINISHED
Object Corwin 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: Corwin | Statement: [Jeff Corwin, familyName, Corwin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Corwin
Context triple: [Jeff Corwin, familyName, Corwin]
  • A. Corwin chosen
    Corwin is a surname most notably associated with Jonathan Corwin, a judge involved in the Salem witch trials in 17th-century Massachusetts.
  • B. Eldred
    Eldred is a small borough located in McKean County in northern Pennsylvania, known for its rural character and local community.
  • C. Eldred
    Eldred is the lesser-known first name of the acclaimed American actor Gregory Peck, a major star of classic Hollywood cinema.
  • D. Eldred
    Eldred is a masculine given name of English origin, historically used both as a first and middle name.
  • E. Dirksen
    Dirksen is a surname most notably associated with Everett Dirksen, a prominent mid-20th-century American politician and U.S. Senate Minority Leader.
  • 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_69e0b4b0e79c8190bd61f22ef1329fa8 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e675e104f081909d17c1963a5db528 completed April 20, 2026, 6:52 p.m.
Created at: April 16, 2026, 10:31 a.m.