Triple

T8669550
Position Surface form Disambiguated ID Type / Status
Subject David Levien E205759 entity
Predicate notableWork P4 FINISHED
Object Wormwood
"Wormwood" is a crime novel by David Levien, known for its gritty, suspenseful storytelling and exploration of the darker sides of human nature.
 E750066 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: Wormwood | Statement: [David Levien, notableWork, Wormwood]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Wormwood
Context triple: [David Levien, notableWork, Wormwood]
  • A. Ambrosia
    Ambrosia is a figure from Greek mythology, known as a daughter of the Titan Atlas.
  • B. Ambrosia
    Ambrosia is a Thoroughbred racehorse known for competing on the track in professional horse racing events.
  • C. Branigin
    Branigin is a surname most notably associated with Roger D. Branigin, who served as the 42nd governor of Indiana.
  • D. Herse
    Herse is a small, irregular outer moon of Jupiter belonging to the planet’s distant, retrograde satellite group.
  • E. Mandragora
    Mandragora is a small genus of often toxic, folklore-famous flowering plants known as mandrakes, traditionally associated with magical and medicinal uses.
  • 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: Wormwood
Triple: [David Levien, notableWork, Wormwood]
Generated description
"Wormwood" is a crime novel by David Levien, known for its gritty, suspenseful storytelling and exploration of the darker sides of human nature.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Wormwood
Target entity description: "Wormwood" is a crime novel by David Levien, known for its gritty, suspenseful storytelling and exploration of the darker sides of human nature.
  • A. Ambrosia
    Ambrosia is a figure from Greek mythology, known as a daughter of the Titan Atlas.
  • B. Ambrosia
    Ambrosia is a Thoroughbred racehorse known for competing on the track in professional horse racing events.
  • C. Branigin
    Branigin is a surname most notably associated with Roger D. Branigin, who served as the 42nd governor of Indiana.
  • D. Herse
    Herse is a small, irregular outer moon of Jupiter belonging to the planet’s distant, retrograde satellite group.
  • E. Mandragora
    Mandragora is a small genus of often toxic, folklore-famous flowering plants known as mandrakes, traditionally associated with magical and medicinal uses.
  • 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_69ca83516ae88190aefe034b3bc589e3 completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc4917cb9881909a73b74e54250613 completed March 31, 2026, 10:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69cecd2b996481908da33fbd95494376 completed April 2, 2026, 8:10 p.m.
NEDg Description generation batch_69cece8fcbcc8190832a66287bc8f833 completed April 2, 2026, 8:16 p.m.
NED2 Entity disambiguation (via description) batch_69cecff48600819086a15700cb947056 completed April 2, 2026, 8:22 p.m.
Created at: March 30, 2026, 6:31 p.m.