Triple

T2926007
Position Surface form Disambiguated ID Type / Status
Subject Nathaniel Lyon E78845 entity
Predicate fullName P16 FINISHED
Object Nathaniel Lyon E164480 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: Nathaniel Lyon | Statement: [Nathaniel Lyon, fullName, Nathaniel Lyon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nathaniel Lyon
Context triple: [Nathaniel Lyon, fullName, Nathaniel Lyon]
  • A. Nathaniel Lyon chosen
    Nathaniel Lyon was a Union Army general in the American Civil War, notable as the first Union general killed in combat during the conflict.
  • B. John J. Parker
    John J. Parker was a prominent American judge who served on the U.S. Court of Appeals for the Fourth Circuit and was once a nominee to the U.S. Supreme Court.
  • C. John Nicholson
    John Nicholson was a British Army officer in colonial India renowned for his fierce leadership and pivotal role in suppressing the Indian Rebellion of 1857.
  • D. Henry Gage
    Henry Gage was an American politician and lawyer who served as the 20th governor of California from 1899 to 1903.
  • E. William Mills
    William Mills is a personal name shared by multiple notable individuals across fields such as politics, sports, and academia.
  • 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_69ad8b0d40b481908bc2a5fa2e73c3fb completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad97c1e9c08190bcec80bc3262697a completed March 8, 2026, 3:37 p.m.
NED1 Entity disambiguation (via context triple) batch_69b0563a81788190b94fab34e41a76e7 completed March 10, 2026, 5:34 p.m.
Created at: March 8, 2026, 2:55 p.m.