Triple

T5402823
Position Surface form Disambiguated ID Type / Status
Subject On Eagle’s Wings E120819 entity
Predicate hasAuthor P4244 FINISHED
Object A. E. Southon E519214 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: A. E. Southon | Statement: [On Eagle’s Wings, hasAuthor, A. E. Southon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: A. E. Southon
Context triple: [On Eagle’s Wings, hasAuthor, A. E. Southon]
  • A. A. E. Southon chosen
    A. E. Southon was an author known for writing the religious work "On Eagle’s Wings."
  • B. J. G. Quintel
    J. G. Quintel is an American animator, writer, and voice actor best known for creating the Cartoon Network series "Regular Show."
  • C. H. M. Harwood
    H. M. Harwood was a British playwright and screenwriter active in the early 20th century, known for his work on stage adaptations and films.
  • D. Edward E. Smith
    Edward E. Smith was an American science fiction author best known for his pioneering space opera novels, particularly the Lensman and Skylark series.
  • E. Harold Speed
    Harold Speed was a British painter and influential art teacher best known for his classic instructional books on drawing and painting.
  • 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_69bd46391c0c81909fa484446732b6a3 completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd87731c1c81909a4dc865282bd289 completed March 20, 2026, 5:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf411d608c8190a672e336e6f3954d completed March 22, 2026, 1:08 a.m.
Created at: March 20, 2026, 2:04 p.m.