Triple

T18985206
Position Surface form Disambiguated ID Type / Status
Subject Lexi Underwood E464537 entity
Predicate hasRole P161 FINISHED
Object Isabella
Isabella is a fictional character portrayed by American actress Lexi Underwood.
E1352403 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: Isabella | Statement: [Lexi Underwood, hasRole, Isabella]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Isabella
Context triple: [Lexi Underwood, hasRole, Isabella]
  • A. Isabella
    Isabella is a virtuous and resourceful young noblewoman in Horace Walpole’s Gothic novel "The Castle of Otranto," whose peril and resistance drive much of the story’s suspense and drama.
  • B. Isabella
    Isabella was an English princess of the 13th century, daughter of King John of England, who became Lady de Coucy through marriage into the French nobility.
  • C. Isabella
    Isabella is the given name of Lady Gregory, the influential Irish dramatist, folklorist, and co-founder of Dublin’s Abbey Theatre.
  • D. Isabella
    Isabella of Valois was a French princess who became Queen of England as the child bride of King Richard II during the late 14th century.
  • E. Isabella
    Isabella was a 15th-century Portuguese infanta who became Queen of Castile through her marriage to King John II.
  • 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: Isabella
Triple: [Lexi Underwood, hasRole, Isabella]
Generated description
Isabella is a fictional character portrayed by American actress Lexi Underwood.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Isabella
Target entity description: Isabella is a fictional character portrayed by American actress Lexi Underwood.
  • A. Isabella
    Isabella is a Danish princess, the eldest daughter of Crown Prince Frederik and Crown Princess Mary and a member of the Danish royal family.
  • B. Isabella
    Isabella is a virtuous and resourceful young noblewoman in Horace Walpole’s Gothic novel "The Castle of Otranto," whose peril and resistance drive much of the story’s suspense and drama.
  • C. Isabella
    Isabella is a character in the play "The Changeling," serving as a subplot figure whose actions and relationships mirror and contrast the main plot’s themes of desire and deception.
  • D. Isabella
    Isabella is a feminine given name of Spanish and Italian origin, derived from Elizabeth and widely used across many cultures.
  • E. Isabella
    Isabella was a medieval European queen consort, notably Isabella of France who became Queen of England as the wife of Edward II and played a key role in his overthrow.
  • 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_69d8dd008af48190a97ff1c6488edf1b completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d65f7f08819088f56e8e030851b1 completed April 20, 2026, 7:31 a.m.
NED1 Entity disambiguation (via context triple) batch_6a05ad4717f48190a950ac569b8bcf12 completed May 14, 2026, 11:08 a.m.
NEDg Description generation batch_6a05aedf05c4819096ac6a61ada4b310 completed May 14, 2026, 11:15 a.m.
NED2 Entity disambiguation (via description) batch_6a05afe523208190a97142cd8e3b887b completed May 14, 2026, 11:20 a.m.
Created at: April 10, 2026, 12:01 p.m.