Triple

T15008160
Position Surface form Disambiguated ID Type / Status
Subject Anathema Device E377761 entity
Predicate familyName P18 FINISHED
Object Device
Device is the surname of Anathema Device, a witch and key character in Neil Gaiman and Terry Pratchett’s novel "Good Omens."
E1132156 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: Device | Statement: [Anathema Device, familyName, Device]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Device
Context triple: [Anathema Device, familyName, Device]
  • A. Device Stage
    Device Stage is a Windows feature that provides a centralized, task-based interface for managing and interacting with connected devices such as printers, cameras, and phones.
  • B. Gadget
    Gadget is the bumbling yet well-intentioned cyborg detective protagonist of the animated series "Inspector Gadget," known for his numerous built-in mechanical devices.
  • C. Mobile
    Mobile is a small coastal community in Newfoundland and Labrador, Canada, located on the Avalon Peninsula south of St. John’s.
  • D. Mobile
    Mobile is a historic port city on Alabama’s Gulf Coast known for its shipbuilding, cultural heritage, and hosting one of the oldest Mardi Gras celebrations in the United States.
  • E. Platform
    Platform is a competitive program at the Toronto International Film Festival that showcases bold, director-driven international cinema.
  • 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: Device
Triple: [Anathema Device, familyName, Device]
Generated description
Device is the surname of Anathema Device, a witch and key character in Neil Gaiman and Terry Pratchett’s novel "Good Omens."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Device
Target entity description: Device is the surname of Anathema Device, a witch and key character in Neil Gaiman and Terry Pratchett’s novel "Good Omens."
  • A. Device Stage
    Device Stage is a Windows feature that provides a centralized, task-based interface for managing and interacting with connected devices such as printers, cameras, and phones.
  • B. Gadget
    Gadget is the bumbling yet well-intentioned cyborg detective protagonist of the animated series "Inspector Gadget," known for his numerous built-in mechanical devices.
  • C. Mobile
    Mobile is a small coastal community in Newfoundland and Labrador, Canada, located on the Avalon Peninsula south of St. John’s.
  • D. Mobile
    Mobile is a historic port city on Alabama’s Gulf Coast known for its shipbuilding, cultural heritage, and hosting one of the oldest Mardi Gras celebrations in the United States.
  • E. Platform
    Platform is a competitive program at the Toronto International Film Festival that showcases bold, director-driven international cinema.
  • 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_69d85cd3a3c881908c71fc424d459c17 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded73348d4819091d9e7f1b0fed822 completed April 15, 2026, 12:09 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe96a52bb08190961e3f18d751fe2a completed May 9, 2026, 2:06 a.m.
NEDg Description generation batch_69fe98bf505c819089740180a763db34 completed May 9, 2026, 2:15 a.m.
NED2 Entity disambiguation (via description) batch_69fe9aab47888190812ff9732380e124 completed May 9, 2026, 2:23 a.m.
Created at: April 10, 2026, 2:55 a.m.