Triple

T10390110
Position Surface form Disambiguated ID Type / Status
Subject Iris Taylor E244868 entity
Predicate spouse P13 FINISHED
Object Robert W. Taylor E48702 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: Robert W. Taylor | Statement: [Iris Taylor, spouse, Robert W. Taylor]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Robert W. Taylor
Context triple: [Iris Taylor, spouse, Robert W. Taylor]
  • A. Robert W. Taylor chosen
    Robert W. Taylor was an influential American computer scientist and research manager who played a key role in the development of ARPANET and modern computer networking.
  • B. Glen H. Taylor
    Glen H. Taylor was an Idaho senator and progressive Democrat best known for serving as Henry A. Wallace’s vice-presidential running mate on the Progressive Party ticket in the 1948 U.S. presidential election.
  • C. Bob Taylor
    Bob Taylor is a disturbed and enigmatic character in the 2013 thriller film "Prisoners," whose behavior and backstory play a key role in the movie’s central kidnapping investigation.
  • D. Clark C. Taylor
    Clark C. Taylor is the son of American folk singer and songwriter Judy Collins.
  • E. Stanley E. Johnson
    Stanley E. Johnson is an editor best known for his work on the classic American children's novel "Old Yeller."
  • 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_69d381b5116081908d85227bab6d3c0c completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4e9b4f7d08190bcb16d3b4c8f22ad completed April 7, 2026, 11:25 a.m.
NED1 Entity disambiguation (via context triple) batch_69d8dc1eb7348190b9f3c473443bacf3 completed April 10, 2026, 11:16 a.m.
Created at: April 6, 2026, 12:05 p.m.