Triple

T13983890
Position Surface form Disambiguated ID Type / Status
Subject International Harvester E336383 entity
Predicate foundedBy P104 FINISHED
Object Norman B. Ream 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: Norman B. Ream | Statement: [International Harvester, foundedBy, Norman B. Ream]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Norman B. Ream
Context triple: [International Harvester, foundedBy, Norman B. Ream]
  • A. Norman B. Ream chosen
    Norman B. Ream was an American businessman and financier active in the late 19th and early 20th centuries, known for his roles on the boards of major industrial and financial corporations.
  • B. Norman C. Francis
    Norman C. Francis is a prominent American educator and longtime president of Xavier University of Louisiana, widely recognized for his leadership in higher education and civil rights.
  • C. Norman T. Herman
    Norman T. Herman is a film producer best known for his work on the 1973 British horror movie "The Legend of Hell House."
  • D. Walter S. Amos
    Walter S. Amos was an American geologist and cave explorer best known for discovering Skyline Caverns in Virginia.
  • E. Ralph E. Winters
    Ralph E. Winters was an Academy Award–winning Canadian-American film editor known for his work on numerous major Hollywood films throughout the mid-20th century.
  • 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_69d81c639e808190a0e4b4f3d31c6a59 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2ea2e8808190a1203a6386224bd8 completed April 14, 2026, 12:10 p.m.
Created at: April 9, 2026, 10:18 p.m.