Triple

T14974146
Position Surface form Disambiguated ID Type / Status
Subject Thomas Willis Cobb E373399 entity
Predicate hasNameInNativeLanguage P1435 FINISHED
Object Thomas Willis Cobb E373399 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: Thomas Willis Cobb | Statement: [Thomas Willis Cobb, hasNameInNativeLanguage, Thomas Willis Cobb]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Thomas Willis Cobb
Context triple: [Thomas Willis Cobb, hasNameInNativeLanguage, Thomas Willis Cobb]
  • A. Thomas Willis Cobb chosen
    Thomas Willis Cobb was a 19th-century American politician and judge from Georgia who served in the U.S. Congress and on the state’s superior court.
  • B. Thomas Jones Woodward
    Thomas Jones Woodward is the birth name of Tom Jones, the Welsh singer famed for powerful vocals and hits like "It's Not Unusual" and "Delilah."
  • C. Robert H. Cobb
    Robert H. Cobb was an American restaurateur best known as the owner of the Brown Derby restaurant in Hollywood and the creator of the Cobb salad.
  • D. J. Franklin Bell
    J. Franklin Bell was a U.S. Army general and Medal of Honor recipient who served as Army Chief of Staff in the early 20th century.
  • E. Smith Seckman Reid
    Smith Seckman Reid is an engineering design and consulting firm known for providing building systems and infrastructure services on major projects, including large sports and entertainment venues.
  • 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_69d85ccbbcd48190acb56e7cf104d8ad completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded6e767608190940eb6f16ea97451 completed April 15, 2026, 12:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff01d6ddbc81908b010a54ee728dfe completed May 9, 2026, 9:43 a.m.
Created at: April 10, 2026, 2:50 a.m.