Triple

T10907887
Position Surface form Disambiguated ID Type / Status
Subject Redbone E257617 entity
Predicate writer P1360 FINISHED
Object William Collins E857381 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: William Collins | Statement: [Redbone, writer, William Collins]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: William Collins
Context triple: [Redbone, writer, William Collins]
  • A. William Collins
    William Collins was a Scottish publisher and founder of the notable publishing house William Collins, Sons, which later became part of HarperCollins.
  • B. William Collins chosen
    William Collins is a pompous clergyman and the obsequious cousin of the Bennet family who stands to inherit their Longbourn estate in Jane Austen’s novel "Pride and Prejudice."
  • C. Thomas Hood
    Thomas Hood was a 19th-century English poet, author, and humorist best known for his comic verse and poems with strong social and humanitarian themes.
  • D. William Cowper
    William Cowper was an 18th-century English poet and hymn writer known for his reflective, nature-infused verse and contributions to the Olney Hymns.
  • E. Henry Herbert Southey
    Henry Herbert Southey was an English physician and medical writer of the early 19th century, noted for his clinical practice and contributions to medical literature.
  • 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_69d6aa8550c8819095508a2ed9acf3db completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d7706756d081908ed29c68d81df688 completed April 9, 2026, 9:24 a.m.
NED1 Entity disambiguation (via context triple) batch_69e1554fc61c8190a0354e2f24cb62e4 completed April 16, 2026, 9:31 p.m.
Created at: April 8, 2026, 9:22 p.m.