Triple

T14737331
Position Surface form Disambiguated ID Type / Status
Subject Jean Hagen E346246 entity
Predicate spouse P13 FINISHED
Object Tom Seidel E346246 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 Seidel | Statement: [Jean Hagen, spouse, Tom Seidel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tom Seidel
Context triple: [Jean Hagen, spouse, Tom Seidel]
  • A. Tom Seidel chosen
    Tom Seidel was the husband of American actress Jean Hagen, known for her role in the classic film "Singin' in the Rain."
  • B. Chad Seiter
    Chad Seiter is an American composer and orchestrator known for his work on television series, films, and video game soundtracks.
  • C. Mike Sievert
    Mike Sievert is an American business executive best known for leading T-Mobile US through its high-growth, "Un-carrier" strategy and major merger with Sprint.
  • D. Mike Schuler
    Mike Schuler is an American basketball coach best known for his successful tenure as head coach of the Portland Trail Blazers in the late 1980s.
  • E. Richard Seifert
    Richard Seifert was a prominent 20th-century British architect known for his influential and often controversial modernist high-rise buildings across London.
  • 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_69d822e6f1c88190bc494d491a907114 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69dec73264848190be23c5f0260cbe13 completed April 14, 2026, 11:01 p.m.
NED1 Entity disambiguation (via context triple) batch_69ff133571008190b7e7867208095b90 completed May 9, 2026, 10:57 a.m.
Created at: April 10, 2026, 1:29 a.m.