Triple

T928523
Position Surface form Disambiguated ID Type / Status
Subject Oryx and Crake E20039 entity
Predicate mainCharacter P1183 FINISHED
Object Snowman
Snowman is the post-apocalyptic survivor and narrator of Margaret Atwood’s dystopian novel "Oryx and Crake," through whose perspective the story’s ruined world and its origins are revealed.
 E110034 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: Snowman | Statement: [Oryx and Crake, mainCharacter, Snowman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Snowman
Context triple: [Oryx and Crake, mainCharacter, Snowman]
  • A. Thunder Snow
    Thunder Snow is a prominent Irish-bred Thoroughbred racehorse best known for winning back-to-back Dubai World Cups in 2018 and 2019.
  • B. Snowlets
    Snowlets are the four snowy owl mascots created to represent the 1998 Winter Olympics in Nagano, Japan.
  • C. Edelweiss
    "Edelweiss" is a gentle, nostalgic song from the musical *The Sound of Music*, widely recognized as one of Richard Rodgers and Oscar Hammerstein II’s most beloved compositions.
  • D. Puckman
    Puckman is the ice hockey–themed mascot representing Rensselaer Polytechnic Institute’s athletic teams.
  • E. Snowflake
    Snowflake is a cloud-based data warehousing platform known for its scalable, high-performance analytics and separation of storage and compute.
  • 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: Snowman
Triple: [Oryx and Crake, mainCharacter, Snowman]
Generated description
Snowman is the post-apocalyptic survivor and narrator of Margaret Atwood’s dystopian novel "Oryx and Crake," through whose perspective the story’s ruined world and its origins are revealed.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Snowman
Target entity description: Snowman is the post-apocalyptic survivor and narrator of Margaret Atwood’s dystopian novel "Oryx and Crake," through whose perspective the story’s ruined world and its origins are revealed.
  • A. Thunder Snow
    Thunder Snow is a prominent Irish-bred Thoroughbred racehorse best known for winning back-to-back Dubai World Cups in 2018 and 2019.
  • B. Snowlets
    Snowlets are the four snowy owl mascots created to represent the 1998 Winter Olympics in Nagano, Japan.
  • C. Edelweiss
    "Edelweiss" is a gentle, nostalgic song from the musical *The Sound of Music*, widely recognized as one of Richard Rodgers and Oscar Hammerstein II’s most beloved compositions.
  • D. Puckman
    Puckman is the ice hockey–themed mascot representing Rensselaer Polytechnic Institute’s athletic teams.
  • E. Snowflake
    Snowflake is a cloud-based data warehousing platform known for its scalable, high-performance analytics and separation of storage and compute.
  • 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_69a493af3dc48190adb7263e6e445ea1 completed March 1, 2026, 7:29 p.m.
NER Named-entity recognition batch_69a4b34775ac8190aabbd047a36cec6b completed March 1, 2026, 9:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69a7ee0f01ac8190b280829dbc5ef102 completed March 4, 2026, 8:32 a.m.
NEDg Description generation batch_69a7f45b5b808190906419754d355feb completed March 4, 2026, 8:59 a.m.
NED2 Entity disambiguation (via description) batch_69a7f50a2a108190b2748c7e9bba3e06 completed March 4, 2026, 9:02 a.m.
Created at: March 1, 2026, 7:40 p.m.