Triple

T22204219
Position Surface form Disambiguated ID Type / Status
Subject Leonidas Polk E548761 entity
Predicate familyName P18 FINISHED
Object Polk 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: Polk | Statement: [Leonidas Polk, familyName, Polk]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Polk
Context triple: [Leonidas Polk, familyName, Polk]
  • A. Polk
    Polk is a Chicago Transit Authority 'L' station on the Pink Line serving the Near West Side near the Illinois Medical District.
  • B. Polk chosen
    Polk is a surname most prominently associated with James K. Polk, the 11th president of the United States.
  • C. Johnson B
    Johnson B is a standard astronomical photometric filter that measures stellar brightness in the blue portion of the visible spectrum.
  • D. Willis Jefferson Polk
    Willis Jefferson Polk was an influential American architect of the late 19th and early 20th centuries, best known for shaping the architectural landscape of San Francisco with prominent commercial and residential buildings.
  • E. Adlai
    Adlai is a masculine given name most notably associated with several generations of American politicians in the Stevenson family.
  • 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_69e11e3ecc7c8190b5f94cd8f42e9d37 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f12b25eac4819094b3c50027ed66db completed April 28, 2026, 9:48 p.m.
Created at: April 16, 2026, 8:36 p.m.