Triple

T14213670
Position Surface form Disambiguated ID Type / Status
Subject Epic E352292 entity
Predicate mainCharacter P1183 FINISHED
Object Mary Katherine
Mary Katherine is the adventurous teenage heroine of the animated fantasy film "Epic," who becomes shrunken and drawn into a hidden forest world where she helps defend nature from dark forces.
E1088124 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: Mary Katherine | Statement: [Epic, mainCharacter, Mary Katherine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mary Katherine
Context triple: [Epic, mainCharacter, Mary Katherine]
  • A. Katherine
    Katherine is the central protagonist of the story "The Well," around whom the narrative’s main events and conflicts revolve.
  • B. Katherine
    Katherine is a feminine given name of Greek origin, commonly associated with meanings related to purity.
  • C. Katherine
    Katherine is a regional town in Australia's Northern Territory, known as a key service and transport hub near Nitmiluk (Katherine Gorge) National Park.
  • D. Katherine
    Katherine is one of the witty noblewomen in William Shakespeare’s comedy "Love’s Labour’s Lost," known for her sharp dialogue and role in the play’s romantic entanglements.
  • E. Katherine
    Katherine is the daughter of Evelyn Mulwray in the 1974 film noir "Chinatown," whose parentage is central to the movie's mystery and emotional impact.
  • 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: Mary Katherine
Triple: [Epic, mainCharacter, Mary Katherine]
Generated description
Mary Katherine is the adventurous teenage heroine of the animated fantasy film "Epic," who becomes shrunken and drawn into a hidden forest world where she helps defend nature from dark forces.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mary Katherine
Target entity description: Mary Katherine is the adventurous teenage heroine of the animated fantasy film "Epic," who becomes shrunken and drawn into a hidden forest world where she helps defend nature from dark forces.
  • A. Katherine
    Katherine is the daughter of Evelyn Mulwray in the 1974 film noir "Chinatown," whose parentage is central to the movie's mystery and emotional impact.
  • B. Katherine
    Katherine is the central protagonist of the story "The Well," around whom the narrative’s main events and conflicts revolve.
  • C. Katherine
    Katherine is a feminine given name of Greek origin, commonly associated with meanings related to purity.
  • D. Katherine
    Katherine is the mother of Thomasin.
  • E. Katherine
    Katherine is a regional town in Australia's Northern Territory, known as a key service and transport hub near Nitmiluk (Katherine Gorge) National Park.
  • 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_69d8278a06e481908b5d6af0a8afe737 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de620f07bc81909212dcd1c91b5f95 completed April 14, 2026, 3:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd280e56e0819097e2aa2b28f19257 completed May 8, 2026, 12:02 a.m.
NEDg Description generation batch_69fd2b874ea081908c5a3958bd6bb5a8 completed May 8, 2026, 12:17 a.m.
NED2 Entity disambiguation (via description) batch_69fd2c6ce098819084a7e322c9582557 completed May 8, 2026, 12:21 a.m.
Created at: April 10, 2026, 1:06 a.m.