Triple

T3313929
Position Surface form Disambiguated ID Type / Status
Subject A Song of Ice and Fire E69635 entity
Predicate hasCharacter P2308 FINISHED
Object Shae
Shae is a young camp follower in George R.R. Martin’s A Song of Ice and Fire series who becomes Tyrion Lannister’s lover and plays a pivotal role in his downfall.
 E347369 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: Shae | Statement: [A Song of Ice and Fire, hasCharacter, Shae]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Shae
Context triple: [A Song of Ice and Fire, hasCharacter, Shae]
  • A. Baelen
    Baelen is a small municipality in the province of Liège in eastern Belgium, near the German border.
  • B. Bayta Darell
    Bayta Darell is a pivotal character in Isaac Asimov's Foundation series, known for her crucial role in thwarting the Mule's conquest in "Foundation and Empire."
  • C. Channah
    Channah is a given name, often considered a variant of the Hebrew name Hannah, traditionally associated with grace or favor.
  • D. Jaq
    Jaq is one of Cinderella’s loyal mouse friends in Disney’s 1950 animated film, known for his bravery, resourcefulness, and comic personality.
  • E. Serein
    Serein is a river in central France that flows through the Burgundy region before joining the Yonne River.
  • 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: Shae
Triple: [A Song of Ice and Fire, hasCharacter, Shae]
Generated description
Shae is a young camp follower in George R.R. Martin’s A Song of Ice and Fire series who becomes Tyrion Lannister’s lover and plays a pivotal role in his downfall.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Shae
Target entity description: Shae is a young camp follower in George R.R. Martin’s A Song of Ice and Fire series who becomes Tyrion Lannister’s lover and plays a pivotal role in his downfall.
  • A. Baelen
    Baelen is a small municipality in the province of Liège in eastern Belgium, near the German border.
  • B. Bayta Darell
    Bayta Darell is a pivotal character in Isaac Asimov's Foundation series, known for her crucial role in thwarting the Mule's conquest in "Foundation and Empire."
  • C. Channah
    Channah is a given name, often considered a variant of the Hebrew name Hannah, traditionally associated with grace or favor.
  • D. Jaq
    Jaq is one of Cinderella’s loyal mouse friends in Disney’s 1950 animated film, known for his bravery, resourcefulness, and comic personality.
  • E. Serein
    Serein is a river in central France that flows through the Burgundy region before joining the Yonne River.
  • 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_69ad85a0bb048190a5458d2738012d61 completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb0ef548481908b3aabc7052c70d8 completed March 8, 2026, 5:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69b2f3f760348190abd8854c369cb41b completed March 12, 2026, 5:12 p.m.
NEDg Description generation batch_69b2fa1dafe8819094905ac930fd1761 completed March 12, 2026, 5:38 p.m.
NED2 Entity disambiguation (via description) batch_69b312b6e224819080957998acbed524 completed March 12, 2026, 7:23 p.m.
Created at: March 8, 2026, 3:11 p.m.