Triple

T14639093
Position Surface form Disambiguated ID Type / Status
Subject Valyrian culture E343677 entity
Predicate writingSystem P454 FINISHED
Object Valyrian script
Valyrian script is a fictional writing system from the world of Game of Thrones, used to represent the languages of the ancient Valyrian civilization.
 E1306922 NE FINISHED

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.

NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Valyrian script
Context triple: [Valyrian culture, writingSystem, Valyrian script]
  • A. Aurebesh
    Aurebesh is the standardized writing system used to represent the Galactic Basic language in the Star Wars universe.
  • B. Tirhuta script
    Tirhuta script is a traditional Brahmic writing system historically used for the Maithili language of the Mithila region in India and Nepal.
  • C. Khitan script
    The Khitan script was an ancient writing system used by the Khitan people of northern China and Central Asia, notable for its complex logographic and syllabic forms and its role in recording the languages of the Liao and Qara Khitai empires.
  • D. Insular script
    Insular script is a medieval style of writing developed in the British Isles, notable for its distinctive rounded letterforms and use in early Irish and Anglo-Saxon manuscripts.
  • E. Sibe script
    The Sibe script is an alphabetic writing system derived from the Manchu script, used primarily to write the Sibe language spoken by the Sibe people in China.
  • 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: Valyrian script
Triple: [Valyrian culture, writingSystem, Valyrian script]
Generated description
Valyrian script is a fictional writing system from the world of Game of Thrones, used to represent the languages of the ancient Valyrian civilization.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Valyrian script
Target entity description: Valyrian script is a fictional writing system from the world of Game of Thrones, used to represent the languages of the ancient Valyrian civilization.
  • A. Aurebesh
    Aurebesh is the standardized writing system used to represent the Galactic Basic language in the Star Wars universe.
  • B. Tirhuta script
    Tirhuta script is a traditional Brahmic writing system historically used for the Maithili language of the Mithila region in India and Nepal.
  • C. Khitan script
    The Khitan script was an ancient writing system used by the Khitan people of northern China and Central Asia, notable for its complex logographic and syllabic forms and its role in recording the languages of the Liao and Qara Khitai empires.
  • D. Insular script
    Insular script is a medieval style of writing developed in the British Isles, notable for its distinctive rounded letterforms and use in early Irish and Anglo-Saxon manuscripts.
  • E. Sibe script
    The Sibe script is an alphabetic writing system derived from the Manchu script, used primarily to write the Sibe language spoken by the Sibe people in China.
  • F. None of above. chosen

Provenance (4 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_69d822e1a2cc81908e5bb93cf61ce3cc completed April 9, 2026, 10:06 p.m.
NED1 Entity disambiguation (via context triple) batch_6a037c1a1390819092d68ddc32e4479f completed May 12, 2026, 7:14 p.m.
NEDg Description generation batch_6a037cfd596481909d0c361a11185194 completed May 12, 2026, 7:18 p.m.
NED2 Entity disambiguation (via description) batch_6a037e7bbd1c8190a88f57cdf5bf30f5 completed May 12, 2026, 7:24 p.m.
Created at: April 10, 2026, 1:26 a.m.