Triple

T21059122
Position Surface form Disambiguated ID Type / Status
Subject Palamon E518804 entity
Predicate createdBy P806 FINISHED
Object Geoffrey Chaucer NE NERFINISHED

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: Geoffrey Chaucer | Statement: [Palamon, createdBy, Geoffrey Chaucer]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Geoffrey Chaucer
Context triple: [Palamon, createdBy, Geoffrey Chaucer]
  • A. Geoffrey Chaucer chosen
    Geoffrey Chaucer was a 14th-century English poet, civil servant, and author of "The Canterbury Tales," often regarded as the father of English literature.
  • B. Daniel Chaucer
    Daniel Chaucer is a pseudonym used by the English novelist and critic Ford Madox Ford.
  • C. John Gower
    John Gower was a 14th-century English poet known for his major works in multiple languages, including Middle English, Latin, and Anglo-Norman, and for being a contemporary and friend of Geoffrey Chaucer.
  • D. William Langland
    William Langland was a 14th-century English poet best known as the probable author of the allegorical Middle English poem "Piers Plowman."
  • E. John Lydgate
    John Lydgate was a prolific 15th-century English monk and poet known for his lengthy narrative and allegorical works that helped shape late medieval English literature.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b5053ac48190921529544959e906 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e6fd842e8881909f4ffc4c43b7fa9f completed April 21, 2026, 4:31 a.m.
Created at: April 16, 2026, 2:37 p.m.