Triple

T18773397
Position Surface form Disambiguated ID Type / Status
Subject Ἠώς E459070 entity
Predicate RomanEquivalent P18136 FINISHED
Object Aurora
Aurora is the Roman goddess of the dawn, who renews herself each morning and flies across the sky to announce the arrival of the sun.
 E459066 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: Aurora | Statement: [Ἠώς, RomanEquivalent, Aurora]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Aurora
Context triple: [Ἠώς, RomanEquivalent, Aurora]
  • A. Aurora
    Aurora is the sleeping princess from Disney's animated film "Sleeping Beauty," known for her grace, kindness, and iconic awakening by true love's kiss.
  • B. Aurora
    Aurora was a Russian protected cruiser famed for firing the symbolic shot that signaled the start of the October Revolution in 1917.
  • C. Aurora
    Aurora is a mystical and theosophical treatise by Jakob Böhme that explores the nature of God, creation, and spiritual rebirth through symbolic and visionary theology.
  • D. Aurora
    "Aurora" is a song by Björk from her 2001 album *Vespertine*, noted for its delicate, atmospheric sound and poetic lyrics.
  • E. Aurora
    Aurora is a Bolivian football club commonly known by its short name, Aurora.
  • 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: Aurora
Triple: [Ἠώς, RomanEquivalent, Aurora]
Generated description
Aurora is the Roman goddess of the dawn, who renews herself each morning and flies across the sky to announce the arrival of the sun.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Aurora
Target entity description: Aurora is the Roman goddess of the dawn, who renews herself each morning and flies across the sky to announce the arrival of the sun.
  • A. Aurora chosen
    Aurora is the Roman goddess of the dawn, who renews herself each morning and announces the arrival of the sun.
  • B. Aurora
    Aurora is a feminine given name of Latin origin meaning "dawn," famously borne by figures in mythology, royalty, and popular culture.
  • C. Aurora
    Aurora is a celebrated Baroque fresco by Italian painter Guido Reni, renowned for its graceful depiction of the goddess of dawn leading Apollo’s chariot across the sky.
  • D. Aurora
    Aurora is the sleeping princess from Disney's animated film "Sleeping Beauty," known for her grace, kindness, and iconic awakening by true love's kiss.
  • E. Aurora
    Aurora is a protected entity or realm under the guardianship of the being known as Fauna.
  • 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_69d8d395dba0819087568404508590cb completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e593378a4081909cc1b0856fce7d7d completed April 20, 2026, 2:45 a.m.
NED1 Entity disambiguation (via context triple) batch_6a053d46f1b88190b51ed8af4004c880 completed May 14, 2026, 3:11 a.m.
NEDg Description generation batch_6a053ee038708190a242cb62fee15302 completed May 14, 2026, 3:17 a.m.
NED2 Entity disambiguation (via description) batch_6a053fba29208190ac0ee5a05522a7e2 completed May 14, 2026, 3:21 a.m.
Created at: April 10, 2026, 11:52 a.m.