Triple

T14821492
Position Surface form Disambiguated ID Type / Status
Subject Battle of Winterfell E348461 entity
Predicate featuresDragon P52720 FINISHED
Object Viserion E864457 NE FINISHED

How this triple was built (2 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: Viserion | Statement: [Battle of Winterfell, featuresDragon, Viserion]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Viserion
Context triple: [Battle of Winterfell, featuresDragon, Viserion]
  • A. Viserion chosen
    Viserion is one of Daenerys Targaryen’s three dragons in the "A Song of Ice and Fire" novels and the "Game of Thrones" television series, known for his cream-and-gold coloring and devastating fire.
  • B. Arys
    Arys is a town in southern Kazakhstan known as a key railway junction and transport hub in the region.
  • C. Arys
    Arys is the former German name of the town now known as Orzysz, located in northeastern Poland.
  • D. Thoros of Myr
    Thoros of Myr is a red priest of R'hllor and a hard-drinking warrior known for his fiery sword and role in the Brotherhood Without Banners in George R. R. Martin's A Song of Ice and Fire series.
  • E. Baelor
    "Baelor" is a pivotal and emotionally devastating episode of Game of Thrones’ first season, best known for its shocking execution of a major character and the dramatic turning point it creates in the series.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d822eb8f588190bf53445e730a934f completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69decfe64328819083ce42704cf0602d completed April 14, 2026, 11:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe389bc06c8190a8269c07677d9c35 completed May 8, 2026, 7:25 p.m.
Created at: April 10, 2026, 1:51 a.m.