Triple

T9271671
Position Surface form Disambiguated ID Type / Status
Subject Michele Ridge E222842 entity
Predicate spouse P13 FINISHED
Object Tom Ridge E31269 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: Tom Ridge | Statement: [Michele Ridge, spouse, Tom Ridge]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tom Ridge
Context triple: [Michele Ridge, spouse, Tom Ridge]
  • A. Tom Ridge chosen
    Tom Ridge is an American politician and former governor of Pennsylvania who became the inaugural U.S. Secretary of Homeland Security, helping to shape the nation’s post-9/11 security framework.
  • B. Thomas P. Corbett
    Thomas P. Corbett, better known as Boston Corbett, was the Union Army soldier famed for killing John Wilkes Booth, the assassin of President Abraham Lincoln.
  • C. Thomas H. Kean
    Thomas H. Kean is an American Republican politician and former governor of New Jersey who is best known for chairing the national commission that investigated the September 11, 2001 terrorist attacks.
  • D. John Kean
    John Kean was an American politician and Continental Congress delegate from South Carolina during the Revolutionary era.
  • E. Martin McKee
    Martin McKee is a prominent public health physician and researcher known for his work on health policy, health systems, and the impacts of social and political change on population health.
  • 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_69ca841ffe208190aa7bcffbef2f8379 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd07865790819099b3865a25dae58a completed April 1, 2026, 11:54 a.m.
NED1 Entity disambiguation (via context triple) batch_69d09c2ca500819083ef4aa37f3e3a7f completed April 4, 2026, 5:05 a.m.
Created at: March 30, 2026, 7:33 p.m.