Triple

T6712970
Position Surface form Disambiguated ID Type / Status
Subject John Swan E153192 entity
Predicate familyName P18 FINISHED
Object Swan E280999 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: Swan | Statement: [John Swan, familyName, Swan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Swan
Context triple: [John Swan, familyName, Swan]
  • A. Swan chosen
    Swan is a large, graceful waterbird known for its long neck, white or black plumage, and strong cultural associations with beauty and elegance.
  • B. Swan
    Swan is a small city in Marion County, Iowa, United States.
  • C. Swan King
    Swan King is the romantic nickname of Ludwig II of Bavaria, the 19th-century monarch famed for his fairy-tale castles and patronage of composer Richard Wagner.
  • D. Goose
    Goose was the nickname of Leon "Goose" Goslin, a Hall of Fame American Major League Baseball left fielder known for his powerful hitting in the 1920s and 1930s.
  • E. Seagull
    "Seagull" is a track from Bill Callahan’s 2013 album *Dream River*, known for its atmospheric, introspective folk sound and poetic lyricism.
  • 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_69c68809b4608190a2509ddb5ab87f05 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d121a92c8190a03f384a8aba84da completed March 27, 2026, 6:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69c700948788819087f9b466be337286 completed March 27, 2026, 10:11 p.m.
Created at: March 27, 2026, 2:07 p.m.