Triple

T5491629
Position Surface form Disambiguated ID Type / Status
Subject Jean Case E123714 entity
Predicate spouse P13 FINISHED
Object Steve Case E22153 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: Steve Case | Statement: [Jean Case, spouse, Steve Case]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Steve Case
Context triple: [Jean Case, spouse, Steve Case]
  • A. Steve Case chosen
    Steve Case is an American entrepreneur and investor best known as the co-founder and former CEO of AOL, a pioneering internet services company.
  • B. John Case
    John Case is a relatively common personal name that may refer to multiple individuals across different fields, such as literature, academia, or public life.
  • C. Ray Ozzie
    Ray Ozzie is an American software entrepreneur and technologist best known for creating Lotus Notes and later serving as a key strategic leader at Microsoft.
  • D. Steve Levy
    Steve Levy is an American sportscaster best known for his long-running work as an ESPN anchor and play-by-play commentator, particularly in hockey and football.
  • E. Sean Parker
    Sean Parker is an American entrepreneur and investor best known as the co-founder of Napster and the first president of Facebook.
  • 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_69bd464a2d908190869324ce176779c8 completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd9280403c8190baaa3f7923449a37 completed March 20, 2026, 6:31 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf77b725988190b578ca5b3417d980 completed March 22, 2026, 5:01 a.m.
Created at: March 20, 2026, 2:10 p.m.