Triple

T21106405
Position Surface form Disambiguated ID Type / Status
Subject Robert Day E520055 entity
Predicate notableWork P4 FINISHED
Object The Green Man 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: The Green Man | Statement: [Robert Day, notableWork, The Green Man]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: The Green Man
Context triple: [Robert Day, notableWork, The Green Man]
  • A. The Green Man
    The Green Man is a traditional English pub located in the village of Grantchester near Cambridge.
  • B. The Green Man
    The Green Man is a nickname for Albert DeSalvo, the notorious American serial killer better known as the Boston Strangler.
  • C. The Green Man chosen
    The Green Man is a 1969 comic ghost story novel by British author Kingsley Amis that blends supernatural horror with darkly humorous exploration of middle-aged angst and skepticism.
  • D. “Green Man”
    The Green Man is a legendary figure in European folklore and architecture, typically depicted as a face surrounded by or made from leaves, symbolizing nature, rebirth, and the cycle of growth.
  • E. The Witch's Head
    "The Witch's Head" is an early adventure novel by H. Rider Haggard that blends romance, mystery, and the supernatural in a tale set partly in England and partly in colonial Africa.
  • 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_69e0b509a318819092fbbcb21d1fe603 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e71b62301c819082cfc6cb3cd11c8c completed April 21, 2026, 6:38 a.m.
Created at: April 16, 2026, 2:53 p.m.