Triple

T13337853
Position Surface form Disambiguated ID Type / Status
Subject Daniel Kraus E317743 entity
Predicate notableWork P4 FINISHED
Object Scowler
Scowler is a dark, psychological horror novel by Daniel Kraus that explores family trauma and violence through the eyes of a troubled teenager on an isolated farm.
 E1034910 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: Scowler | Statement: [Daniel Kraus, notableWork, Scowler]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Scowler
Context triple: [Daniel Kraus, notableWork, Scowler]
  • A. Crowl
    Crowl is a surname that serves as a spelling variant of the more common family name Crowell.
  • B. Smargadus
    Smargadus was the exarch of Ravenna who commissioned the Column of Phocas in the Roman Forum in the early 7th century.
  • C. Slammerkin
    "Slammerkin" is a historical novel by Emma Donoghue that follows a poor young woman's struggle for survival and autonomy in 18th-century Britain, exploring themes of class, gender, and desire.
  • D. Blathers
    Blathers is the scholarly owl who runs the museum in the Animal Crossing series, known for his love of fossils and aversion to insects.
  • E. Blagg
    Blagg is a variant form of the surname "Black," typically arising as an alternative spelling in English-speaking regions.
  • 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: Scowler
Triple: [Daniel Kraus, notableWork, Scowler]
Generated description
Scowler is a dark, psychological horror novel by Daniel Kraus that explores family trauma and violence through the eyes of a troubled teenager on an isolated farm.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Scowler
Target entity description: Scowler is a dark, psychological horror novel by Daniel Kraus that explores family trauma and violence through the eyes of a troubled teenager on an isolated farm.
  • A. Crowl
    Crowl is a surname that serves as a spelling variant of the more common family name Crowell.
  • B. Smargadus
    Smargadus was the exarch of Ravenna who commissioned the Column of Phocas in the Roman Forum in the early 7th century.
  • C. Slammerkin
    "Slammerkin" is a historical novel by Emma Donoghue that follows a poor young woman's struggle for survival and autonomy in 18th-century Britain, exploring themes of class, gender, and desire.
  • D. Blathers
    Blathers is the scholarly owl who runs the museum in the Animal Crossing series, known for his love of fossils and aversion to insects.
  • E. Blagg
    Blagg is a variant form of the surname "Black," typically arising as an alternative spelling in English-speaking regions.
  • 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_69d806b5a3c08190b42c267fb092f98a completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d99d00b75c8190af98784c7df904c8 completed April 11, 2026, 12:59 a.m.
NED1 Entity disambiguation (via context triple) batch_69f71f3bb06c8190beaf6dfbba9ff613 completed May 3, 2026, 10:11 a.m.
NEDg Description generation batch_69f720861728819088bc43753d19bef8 completed May 3, 2026, 10:16 a.m.
NED2 Entity disambiguation (via description) batch_69f7212ca3f48190915d73f987ec60d2 completed May 3, 2026, 10:19 a.m.
Created at: April 9, 2026, 9:31 p.m.