Triple

T4810953
Position Surface form Disambiguated ID Type / Status
Subject Giselle E107066 entity
Predicate mainCharacter P1183 FINISHED
Object Myrtha
Myrtha is the powerful and vengeful Queen of the Wilis in the Romantic ballet "Giselle."
 E473179 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: Myrtha | Statement: [Giselle, mainCharacter, Myrtha]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Myrtha
Context triple: [Giselle, mainCharacter, Myrtha]
  • A. Mylasa
    Mylasa was an important ancient city of Caria in southwestern Anatolia, known as a political and religious center, particularly for the worship of Zeus.
  • B. Cleeia
    Cleeia is a lesser-known figure in Greek mythology, identified as a daughter of the Titan Atlas and thus part of the extended divine family associated with the heavens.
  • C. Marella
    Marella is an Italian feminine given name, notably borne by Marella Agnelli, a prominent socialite, art collector, and style icon.
  • D. Aravan
    Aravan is a heroic figure from the Indian epic Mahabharata, revered in various regional traditions and often associated with themes of sacrifice and devotion.
  • E. Benthesikyme
    Benthesikyme is a minor sea goddess in Greek mythology, known primarily as a daughter of Poseidon.
  • 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: Myrtha
Triple: [Giselle, mainCharacter, Myrtha]
Generated description
Myrtha is the powerful and vengeful Queen of the Wilis in the Romantic ballet "Giselle."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Myrtha
Target entity description: Myrtha is the powerful and vengeful Queen of the Wilis in the Romantic ballet "Giselle."
  • A. Mylasa
    Mylasa was an important ancient city of Caria in southwestern Anatolia, known as a political and religious center, particularly for the worship of Zeus.
  • B. Cleeia
    Cleeia is a lesser-known figure in Greek mythology, identified as a daughter of the Titan Atlas and thus part of the extended divine family associated with the heavens.
  • C. Marella
    Marella is an Italian feminine given name, notably borne by Marella Agnelli, a prominent socialite, art collector, and style icon.
  • D. Aravan
    Aravan is a heroic figure from the Indian epic Mahabharata, revered in various regional traditions and often associated with themes of sacrifice and devotion.
  • E. Benthesikyme
    Benthesikyme is a minor sea goddess in Greek mythology, known primarily as a daughter of Poseidon.
  • 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_69bd43f779448190b92885cb70abb6c2 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd6c7b879081908e0c92a67422906e completed March 20, 2026, 3:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69be4dae0008819089c54a3815e578bc completed March 21, 2026, 7:50 a.m.
NEDg Description generation batch_69be501fd0d8819090806aaf6db04945 completed March 21, 2026, 8 a.m.
NED2 Entity disambiguation (via description) batch_69be51951fe8819080a581c8f75147a5 completed March 21, 2026, 8:06 a.m.
Created at: March 20, 2026, 1:23 p.m.