Triple

T22107951
Position Surface form Disambiguated ID Type / Status
Subject Lyman County, South Dakota E546337 entity
Predicate namedFor P63 FINISHED
Object Theodore Lyman 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: Theodore Lyman | Statement: [Lyman County, South Dakota, namedFor, Theodore Lyman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Theodore Lyman
Context triple: [Lyman County, South Dakota, namedFor, Theodore Lyman]
  • A. Theodore Lyman III chosen
    Theodore Lyman III was a 19th-century American politician, philanthropist, and mayor of Boston known for his civic reforms and support of social welfare initiatives.
  • B. Theodore Lyman III
    Theodore Lyman III was an American physicist best known for discovering the Lyman series of ultraviolet spectral lines of hydrogen.
  • C. Samuel C. Phillips
    Samuel C. Phillips was a U.S. Air Force general best known for directing NASA’s Apollo manned lunar landing program.
  • D. Isaac W. Scudder
    Isaac W. Scudder was a 19th-century American politician who served as a U.S. Representative from New Jersey.
  • E. Henry Kitteridge
    Henry Kitteridge is the gentle, patient pharmacist husband of the blunt and complex title character in Elizabeth Strout’s novel "Olive Kitteridge."
  • 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_69e11e378dc08190896d6a51597afd5a completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f1291adc74819092c7753bb6f3768d completed April 28, 2026, 9:39 p.m.
Created at: April 16, 2026, 8:30 p.m.