Triple
T16047572
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ramsay Bolton |
E389262
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object |
Snow
Snow is the surname traditionally given to illegitimate children in the North of Westeros in the "Game of Thrones" / "A Song of Ice and Fire" universe.
|
E649273
|
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: Snow | Statement: [Ramsay Bolton, familyName, Snow]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Snow Context triple: [Ramsay Bolton, familyName, Snow]
-
A.
Snow
Snow is a white color variant of the iMac G3, known for its clean, minimalist appearance among the line’s iconic translucent and colorful designs.
-
B.
Snow
"Snow" is a notable abstract painting by British artist Howard Hodgkin, recognized for its expressive brushwork and evocative use of color to suggest memory and atmosphere.
-
C.
Snow
"Snow" is a song featured on the album *Back to Scratch* by Welsh singer-songwriter Charlotte Church.
-
D.
Snow
"Snow" is a festive song from the 1954 musical film *White Christmas*, celebrated for its nostalgic lyrics about the beauty and romance of wintertime snowfall.
-
E.
Snow
Snow is frozen atmospheric precipitation in the form of ice crystals that accumulate on the ground, often creating white, wintry landscapes.
- 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: Snow Triple: [Ramsay Bolton, familyName, Snow]
Generated description
Snow is the surname traditionally given to illegitimate children in the North of Westeros in the "Game of Thrones" / "A Song of Ice and Fire" universe.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Snow Target entity description: Snow is the surname traditionally given to illegitimate children in the North of Westeros in the "Game of Thrones" / "A Song of Ice and Fire" universe.
-
A.
Snow
chosen
Snow is a common English surname borne by various notable figures in literature, science, and public life.
-
B.
Snow
Snow is the fictional universe in which the manga and anime series "Ka" is set, encompassing its unique world, lore, and settings.
-
C.
Snow
Snow is frozen atmospheric precipitation in the form of ice crystals that accumulate on the ground, often creating white, wintry landscapes.
-
D.
Snow
Snow is a South Korean photo and video messaging app known for its augmented reality filters and stickers, similar in concept to Snapchat.
-
E.
Snow
Snow is a white color variant of the iMac G3, known for its clean, minimalist appearance among the line’s iconic translucent and colorful designs.
- F. None of above.
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_69d86dae698881908327ef2d67706cb9 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e1835eda348190aff492f0ff668cce |
completed | April 17, 2026, 12:48 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffdbddc25481908fca660c4f14eaff |
completed | May 10, 2026, 1:14 a.m. |
| NEDg | Description generation | batch_69ffdc915be88190a0e949fcee608242 |
completed | May 10, 2026, 1:17 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ffdd17239c8190a3c0c4d146a279f7 |
completed | May 10, 2026, 1:19 a.m. |
Created at: April 10, 2026, 4:56 a.m.