Triple

T16524946
Position Surface form Disambiguated ID Type / Status
Subject Ken Follett E401409 entity
Predicate notableWork P4 FINISHED
Object Never
"Never" is a contemporary political thriller novel by Ken Follett that explores how a series of escalating global crises could inadvertently trigger a catastrophic world war.
E1218882 NE FINISHED

How this triple was built (4 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: Never | Statement: [Ken Follett, notableWork, Never]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Never
Context triple: [Ken Follett, notableWork, Never]
  • A. Never
    Never was the historical name of the Russian town now known as Skovorodino in Amur Oblast.
  • B. Ever
    "Ever" is the naming prefix used by Evergreen Marine Corporation for its fleet of container ships, such as the well-known Ever Given.
  • C. Never Did
    "Never Did" is a track from the hip-hop duo Learning, showcasing their style and musical themes.
  • D. Never Been
    "Never Been" is a track featured on Mary J. Blige's acclaimed R&B album "No More Drama."
  • E. No Other
    No Other is a 1974 solo album by American singer-songwriter Gene Clark, acclaimed for its ambitious production, genre-blending sound, and later cult status despite an initially poor commercial reception.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Never
Triple: [Ken Follett, notableWork, Never]
Generated description
"Never" is a contemporary political thriller novel by Ken Follett that explores how a series of escalating global crises could inadvertently trigger a catastrophic world war.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Never
Target entity description: "Never" is a contemporary political thriller novel by Ken Follett that explores how a series of escalating global crises could inadvertently trigger a catastrophic world war.
  • A. Never
    Never was the historical name of the Russian town now known as Skovorodino in Amur Oblast.
  • B. Ever
    "Ever" is the naming prefix used by Evergreen Marine Corporation for its fleet of container ships, such as the well-known Ever Given.
  • C. Never Did
    "Never Did" is a track from the hip-hop duo Learning, showcasing their style and musical themes.
  • D. Never Been
    "Never Been" is a track featured on Mary J. Blige's acclaimed R&B album "No More Drama."
  • E. No Other
    No Other is a 1974 solo album by American singer-songwriter Gene Clark, acclaimed for its ambitious production, genre-blending sound, and later cult status despite an initially poor commercial reception.
  • F. None of above. chosen

Provenance (5 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_69d883838abc8190bc79cb2d41733ce2 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e32ed323c081908218460aa4ae3cf6 completed April 18, 2026, 7:12 a.m.
NED1 Entity disambiguation (via context triple) batch_6a00608b7f6081909912dd575979f8d7 completed May 10, 2026, 10:40 a.m.
NEDg Description generation batch_6a0062b6637c81908a619e36af7d6989 completed May 10, 2026, 10:49 a.m.
NED2 Entity disambiguation (via description) batch_6a00639024d08190a46256691e89953a completed May 10, 2026, 10:53 a.m.
Created at: April 10, 2026, 5:14 a.m.