Triple

T19980958
Position Surface form Disambiguated ID Type / Status
Subject Dark Lady E493813 entity
Predicate hasNotableWork P4 FINISHED
Object Sonnet 147 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: Sonnet 147 | Statement: [Dark Lady, hasNotableWork, Sonnet 147]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sonnet 147
Context triple: [Dark Lady, hasNotableWork, Sonnet 147]
  • A. Sonnet 147 chosen
    Sonnet 147 is one of William Shakespeare’s later, darker sonnets, in which he portrays love as a destructive, feverish madness.
  • B. Sonnet 146
    Sonnet 146 is one of William Shakespeare’s English sonnets, notable for its meditation on the soul, mortality, and the vanity of earthly concerns.
  • C. Sonnet 141
    Sonnet 141 is one of William Shakespeare’s Dark Lady sonnets, exploring the conflict between rational judgment and irrational desire in love.
  • D. Sonnet 135
    Sonnet 135 is one of William Shakespeare’s so-called Dark Lady sonnets, notable for its intricate wordplay on the word “will” and its exploration of desire and sexual punning.
  • E. Sonnet 142
    Sonnet 142 is one of William Shakespeare’s so-called “Dark Lady” sonnets, notable for its exploration of conflicted desire, moral hypocrisy, and unrequited love.
  • 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_69da626a67648190af9653832a3aeced completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e65d12d968819081e315ec4585cd9f completed April 20, 2026, 5:06 p.m.
Created at: April 11, 2026, 3:28 p.m.