Triple

T7092372
Position Surface form Disambiguated ID Type / Status
Subject Sybylla Melvyn E165227 entity
Predicate givenName P17 FINISHED
Object Sybylla
Sybylla is the spirited, independent-minded young heroine and narrator of Miles Franklin’s classic Australian novel "My Brilliant Career."
 E642656 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: Sybylla | Statement: [Sybylla Melvyn, givenName, Sybylla]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sybylla
Context triple: [Sybylla Melvyn, givenName, Sybylla]
  • A. Sybille
    Sybille was a French frigate that took part in the early 19th-century naval engagement known as the Battle of San Domingo.
  • B. The Goddess
    The Goddess is a 1915 American silent drama film starring Anita Stewart, produced by the Vitagraph Company of America.
  • C. Sybil
    Sybil is a character from the fantasy film "The Magic Sword," known for her role in the story’s magical and adventurous narrative.
  • D. Sybil
    Sybil was an illegitimate daughter of King Henry I of England, known primarily through her royal lineage and connections within the Anglo-Norman nobility.
  • E. Sybil
    Sybil is an American R&B and pop singer best known for her late-1980s and early-1990s hits, including popular covers of classic soul songs.
  • 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: Sybylla
Triple: [Sybylla Melvyn, givenName, Sybylla]
Generated description
Sybylla is the spirited, independent-minded young heroine and narrator of Miles Franklin’s classic Australian novel "My Brilliant Career."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sybylla
Target entity description: Sybylla is the spirited, independent-minded young heroine and narrator of Miles Franklin’s classic Australian novel "My Brilliant Career."
  • A. Sybille
    Sybille was a French frigate that took part in the early 19th-century naval engagement known as the Battle of San Domingo.
  • B. The Goddess
    The Goddess is a 1915 American silent drama film starring Anita Stewart, produced by the Vitagraph Company of America.
  • C. Sybil
    Sybil is an American R&B and pop singer best known for her late-1980s and early-1990s hits, including popular covers of classic soul songs.
  • D. Sybil
    Sybil is a character from the fantasy film "The Magic Sword," known for her role in the story’s magical and adventurous narrative.
  • E. Sybil
    Sybil was an illegitimate daughter of King Henry I of England, known primarily through her royal lineage and connections within the Anglo-Norman nobility.
  • 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_69c6887e8c10819091cee237560d32da completed March 27, 2026, 1:39 p.m.
NER Named-entity recognition batch_69c6e532513c8190968eea8a0d3235a0 completed March 27, 2026, 8:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69c79c960484819098228cebccb8c935 completed March 28, 2026, 9:17 a.m.
NEDg Description generation batch_69c79ef0e8448190a8f0a7572ee87f5f completed March 28, 2026, 9:27 a.m.
NED2 Entity disambiguation (via description) batch_69c79fa4e69881909cf991a5d0ab3de9 completed March 28, 2026, 9:30 a.m.
Created at: March 27, 2026, 2:41 p.m.