Triple

T14582439
Position Surface form Disambiguated ID Type / Status
Subject Roxanne Lee E342224 entity
Predicate notableWork P4 FINISHED
Object Arctic Air
Arctic Air is a Canadian television drama series that follows the high-stakes operations of a Yellowknife-based airline in the Arctic.
 E1109138 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: Arctic Air | Statement: [Roxanne Lee, notableWork, Arctic Air]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Arctic Air
Context triple: [Roxanne Lee, notableWork, Arctic Air]
  • A. Wild Arctic
    Wild Arctic is a SeaWorld San Diego themed attraction that simulates a journey to the Arctic, featuring polar wildlife exhibits and immersive cold-climate environments.
  • B. Arctic Heat
    Arctic Heat is the stage name of an American-born individual, likely used as a professional or artistic alias.
  • C. Airnorth
    Airnorth is a regional airline based in northern Australia that operates passenger and charter services across the Northern Territory and surrounding regions.
  • D. Snowy Tundra
    Snowy Tundra is a cold, snow-covered biome in Minecraft characterized by flat, icy terrain, sparse vegetation, and frequent snowfall.
  • E. The Frozen North
    The Frozen North is a creative work by Joe Roberts, likely a narrative or artistic piece set in a harsh, icy environment.
  • 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: Arctic Air
Triple: [Roxanne Lee, notableWork, Arctic Air]
Generated description
Arctic Air is a Canadian television drama series that follows the high-stakes operations of a Yellowknife-based airline in the Arctic.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Arctic Air
Target entity description: Arctic Air is a Canadian television drama series that follows the high-stakes operations of a Yellowknife-based airline in the Arctic.
  • A. Wild Arctic
    Wild Arctic is a SeaWorld San Diego themed attraction that simulates a journey to the Arctic, featuring polar wildlife exhibits and immersive cold-climate environments.
  • B. Arctic Heat
    Arctic Heat is the stage name of an American-born individual, likely used as a professional or artistic alias.
  • C. Airnorth
    Airnorth is a regional airline based in northern Australia that operates passenger and charter services across the Northern Territory and surrounding regions.
  • D. Snowy Tundra
    Snowy Tundra is a cold, snow-covered biome in Minecraft characterized by flat, icy terrain, sparse vegetation, and frequent snowfall.
  • E. The Frozen North
    The Frozen North is a creative work by Joe Roberts, likely a narrative or artistic piece set in a harsh, icy environment.
  • 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_69d822ddc0f081909cd8163c7de298cd completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb41e71748190a1deacc819dd26d3 completed April 14, 2026, 9:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd94ba235c81909e0408ccf2be9628 completed May 8, 2026, 7:46 a.m.
NEDg Description generation batch_69fd9619f33881908e8d95ef09256d34 completed May 8, 2026, 7:51 a.m.
NED2 Entity disambiguation (via description) batch_69fd96e97ec48190aae9b25ce7154802 completed May 8, 2026, 7:55 a.m.
Created at: April 10, 2026, 1:24 a.m.