Triple

T4320196
Position Surface form Disambiguated ID Type / Status
Subject Earl Haig Memorial E96493 entity
Predicate artist P184 FINISHED
Object Alfred Frank Hardiman E440807 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: Alfred Frank Hardiman | Statement: [Earl Haig Memorial, artist, Alfred Frank Hardiman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Alfred Frank Hardiman
Context triple: [Earl Haig Memorial, artist, Alfred Frank Hardiman]
  • A. Alfred Frank Hardiman chosen
    Alfred Frank Hardiman was a British sculptor best known for his monumental public works in the early 20th century.
  • B. Alfred Morton Githens
    Alfred Morton Githens was an American architect known for his influential designs of major public libraries and cultural institutions in the early 20th century.
  • C. William Dewhurst
    William Dewhurst was an actor known for his role in the early 20th-century film "Sabotage."
  • D. George Harding
    George Harding was an architect known for designing the historic Chennai Central railway station in India.
  • E. William Jaggard
    William Jaggard was a London printer and publisher best known for producing the 1623 First Folio of Shakespeare’s plays.
  • 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_69b345422aac81909ddbadae437d122e completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b35114ed2c8190949c5d8032d7b921 completed March 12, 2026, 11:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69b6373b66a481909f66ea8b8659d54a completed March 15, 2026, 4:36 a.m.
Created at: March 12, 2026, 11:12 p.m.