Triple

T20819858
Position Surface form Disambiguated ID Type / Status
Subject Dominion E512543 entity
Predicate setting P1957 FINISHED
Object Vega
Vega is a fictional universe that serves as the backdrop for the Dominion setting, encompassing its worlds, factions, and overarching narrative.
 E1458902 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: Vega | Statement: [Dominion, setting, Vega]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Vega
Context triple: [Dominion, setting, Vega]
  • A. Vega
    Vega is a European small-lift launch vehicle developed by the European Space Agency and partners, primarily used to place light payloads into low Earth orbit.
  • B. Vega
    Vega is a Norwegian island renowned for its UNESCO-listed archipelago, traditional eiderdown harvesting, and rich coastal birdlife.
  • C. Vega
    Vega is an open-source visualization grammar and toolkit for creating, sharing, and exploring interactive data visualizations in a declarative JSON format.
  • D. Vega
    Vega is a masked, claw-wielding Spanish ninja and acrobatic antagonist from the Street Fighter fighting game series.
  • E. Vega
    Vega is a common Spanish surname borne by numerous notable individuals across fields such as entertainment, sports, and politics.
  • 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: Vega
Triple: [Dominion, setting, Vega]
Generated description
Vega is a fictional universe that serves as the backdrop for the Dominion setting, encompassing its worlds, factions, and overarching narrative.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Vega
Target entity description: Vega is a fictional universe that serves as the backdrop for the Dominion setting, encompassing its worlds, factions, and overarching narrative.
  • A. Vega
    Vega is a masked, claw-wielding Spanish ninja and acrobatic antagonist from the Street Fighter fighting game series.
  • B. Vega
    Vega is a European small-lift launch vehicle developed by the European Space Agency and partners, primarily used to place light payloads into low Earth orbit.
  • C. Vega
    Vega is a common Spanish surname borne by numerous notable individuals across fields such as entertainment, sports, and politics.
  • D. Vega
    Vega is an open-source visualization grammar and toolkit for creating, sharing, and exploring interactive data visualizations in a declarative JSON format.
  • E. Vega
    Vega is a residential locality in Haninge Municipality, Stockholm County, Sweden, known for its commuter rail station and growing suburban housing developments.
  • 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_69e0b4ce39108190a6e8e5df4f1c8dc5 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c2f6a65481909a0df78616e185e4 completed April 21, 2026, 12:21 a.m.
NED1 Entity disambiguation (via context triple) batch_6a092774eda48190a2d0039e2ce63648 completed May 17, 2026, 2:27 a.m.
NEDg Description generation batch_6a0928a53e3c8190a8e636f5f1387f73 completed May 17, 2026, 2:32 a.m.
NED2 Entity disambiguation (via description) batch_6a0929485ebc8190ab8bc316b3e802ca completed May 17, 2026, 2:34 a.m.
Created at: April 16, 2026, 12:41 p.m.