Triple

T19153926
Position Surface form Disambiguated ID Type / Status
Subject 18 Poems E468875 entity
Predicate hasPoem P21160 FINISHED
Object The seed-at-zero NE NERFINISHED

How this triple was built (3 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 seed-at-zero | Statement: [18 Poems, hasPoem, The seed-at-zero]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: The seed-at-zero
Context triple: [18 Poems, hasPoem, The seed-at-zero]
  • A. SEED
    SEED is a Stanford University institute focused on promoting innovation and entrepreneurship to drive economic development in emerging and developing economies.
  • B. RDSEED
    RDSEED is an Intel CPU instruction that provides access to a hardware-based random number generator for producing high-quality random seeds.
  • C. Blum–Blum–Shub pseudorandom number generator
    The Blum–Blum–Shub pseudorandom number generator is a cryptographically secure generator based on the hardness of factoring large composite numbers, widely studied in theoretical computer science and cryptography.
  • D. Blum–Micali pseudorandom number generator
    The Blum–Micali pseudorandom number generator is a foundational cryptographic algorithm that produces provably secure pseudorandom bits based on number-theoretic hardness assumptions.
  • E. Towards Zero
    Towards Zero is a classic detective novel by Agatha Christie featuring Superintendent Battle, centered on a complex murder plot at a seaside estate.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: The seed-at-zero
Target entity description: "The seed-at-zero" is a poem featured in Dylan Thomas's influential debut collection "18 Poems," known for its dense imagery and modernist style.
  • A. SEED
    SEED is a Stanford University institute focused on promoting innovation and entrepreneurship to drive economic development in emerging and developing economies.
  • B. RDSEED
    RDSEED is an Intel CPU instruction that provides access to a hardware-based random number generator for producing high-quality random seeds.
  • C. Blum–Blum–Shub pseudorandom number generator
    The Blum–Blum–Shub pseudorandom number generator is a cryptographically secure generator based on the hardness of factoring large composite numbers, widely studied in theoretical computer science and cryptography.
  • D. Blum–Micali pseudorandom number generator
    The Blum–Micali pseudorandom number generator is a foundational cryptographic algorithm that produces provably secure pseudorandom bits based on number-theoretic hardness assumptions.
  • E. Towards Zero
    Towards Zero is a classic detective novel by Agatha Christie featuring Superintendent Battle, centered on a complex murder plot at a seaside estate.
  • F. None of above. chosen

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_69d8dd084ff48190ac0f8c46ee722629 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5eeb81bf08190b0352137eb4a5763 completed April 20, 2026, 9:15 a.m.
Created at: April 10, 2026, 12:06 p.m.