Triple

T2404365
Position Surface form Disambiguated ID Type / Status
Subject Swann Memorial Fountain E50241 entity
Predicate architect P184 FINISHED
Object Wilson Eyre E322469 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: Wilson Eyre | Statement: [Swann Memorial Fountain, architect, Wilson Eyre]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Wilson Eyre
Context triple: [Swann Memorial Fountain, architect, Wilson Eyre]
  • A. Wilson Eyre chosen
    Wilson Eyre was an American architect and influential proponent of the Shingle Style, known for his residential designs and contributions to early 20th-century architecture.
  • B. George Nichols
    George Nichols was a 19th-century American publisher known for issuing notable literary works, including influential satirical and poetic writings.
  • C. George Nichols
    George Nichols was an American actor and film director active during the silent film era.
  • D. James Heald
    James Heald was a notable figure significant enough in South African or local colonial history to have the settlement of Healdtown near Fort Beaufort named in his honor.
  • E. David Horsey
    David Horsey is an American political cartoonist and commentator renowned for his incisive editorial cartoons and multiple Pulitzer Prize-winning work.
  • 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_69a88b0339a88190a1207333cd271cc9 completed March 4, 2026, 7:41 p.m.
NER Named-entity recognition batch_69abc8fa151081909bc6be528b29b315 completed March 7, 2026, 6:43 a.m.
NED1 Entity disambiguation (via context triple) batch_69b20321518c8190a221620074f3428b completed March 12, 2026, 12:04 a.m.
Created at: March 4, 2026, 7:58 p.m.