Triple
T14639272
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Valyrian languages |
E343681
|
entity |
| Predicate | developedBy |
P73
|
FINISHED |
| Object |
David J. Peterson
David J. Peterson is a professional language creator best known for designing constructed languages such as Dothraki and Valyrian for the television series Game of Thrones.
|
E1306928
|
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: David J. Peterson Context triple: [Valyrian languages, developedBy, David J. Peterson]
-
A.
Marc Okrand
Marc Okrand is an American linguist best known for creating the Klingon language for Star Trek and for his work on Native American languages.
-
B.
Dan Mazer
Dan Mazer is a British screenwriter, director, and producer best known for his long-time collaboration with Sacha Baron Cohen on projects like Borat and Brüno.
-
C.
Tharon Musser
Tharon Musser was a pioneering American lighting designer renowned for revolutionizing Broadway lighting with her innovative use of computerized systems on landmark productions.
-
D.
Jeremy Soule
Jeremy Soule is an American composer best known for his atmospheric orchestral soundtracks for video games, particularly the Elder Scrolls and Guild Wars series.
-
E.
Glen Vowell
Glen Vowell is a small Indigenous community in British Columbia, Canada, that serves as one of the village sites of the Gitxsan people.
- 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: David J. Peterson Triple: [Valyrian languages, developedBy, David J. Peterson]
Generated description
David J. Peterson is a professional language creator best known for designing constructed languages such as Dothraki and Valyrian for the television series Game of Thrones.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: David J. Peterson Target entity description: David J. Peterson is a professional language creator best known for designing constructed languages such as Dothraki and Valyrian for the television series Game of Thrones.
-
A.
Marc Okrand
Marc Okrand is an American linguist best known for creating the Klingon language for Star Trek and for his work on Native American languages.
-
B.
Dan Mazer
Dan Mazer is a British screenwriter, director, and producer best known for his long-time collaboration with Sacha Baron Cohen on projects like Borat and Brüno.
-
C.
Tharon Musser
Tharon Musser was a pioneering American lighting designer renowned for revolutionizing Broadway lighting with her innovative use of computerized systems on landmark productions.
-
D.
Jeremy Soule
Jeremy Soule is an American composer best known for his atmospheric orchestral soundtracks for video games, particularly the Elder Scrolls and Guild Wars series.
-
E.
Glen Vowell
Glen Vowell is a small Indigenous community in British Columbia, Canada, that serves as one of the village sites of the Gitxsan people.
- 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.