Triple

T20649983
Position Surface form Disambiguated ID Type / Status
Subject Judith Thompson E507464 entity
Predicate notableWork P4 FINISHED
Object Perfect Pie
Perfect Pie is a Canadian stage play by Judith Thompson that explores memory, trauma, and the complexities of female friendship.
 E1442379 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: Perfect Pie | Statement: [Judith Thompson, notableWork, Perfect Pie]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Perfect Pie
Context triple: [Judith Thompson, notableWork, Perfect Pie]
  • A. The Pie
    The Pie is the spirited horse ridden by Velvet Brown in the classic novel and film "National Velvet."
  • B. Sky in the Pie
    Sky in the Pie is a humorous and imaginative children's poetry collection by British poet Roger McGough.
  • C. Hot Pie
    Hot Pie is a minor character in the "A Song of Ice and Fire" novels and the "Game of Thrones" TV series, known as a former orphan and traveling companion of Arya Stark who becomes a baker.
  • D. PIE
    PIE is the three-letter FAA airport code for St. Pete–Clearwater International Airport serving the Tampa Bay area in Florida.
  • E. PIE
    PIE is the commonly used abbreviation for Proto-Indo-European, the hypothetical prehistoric ancestor of most modern European and many South and Central Asian languages.
  • 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: Perfect Pie
Triple: [Judith Thompson, notableWork, Perfect Pie]
Generated description
Perfect Pie is a Canadian stage play by Judith Thompson that explores memory, trauma, and the complexities of female friendship.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Perfect Pie
Target entity description: Perfect Pie is a Canadian stage play by Judith Thompson that explores memory, trauma, and the complexities of female friendship.
  • A. The Pie
    The Pie is the spirited horse ridden by Velvet Brown in the classic novel and film "National Velvet."
  • B. Sky in the Pie
    Sky in the Pie is a humorous and imaginative children's poetry collection by British poet Roger McGough.
  • C. Hot Pie
    Hot Pie is a minor character in the "A Song of Ice and Fire" novels and the "Game of Thrones" TV series, known as a former orphan and traveling companion of Arya Stark who becomes a baker.
  • D. PIE
    PIE is the three-letter FAA airport code for St. Pete–Clearwater International Airport serving the Tampa Bay area in Florida.
  • E. PIE
    PIE is the commonly used abbreviation for Proto-Indo-European, the hypothetical prehistoric ancestor of most modern European and many South and Central Asian languages.
  • 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_69e0b4bf58c081908e52a4500e03ff83 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6af2133048190a6308074a3b3347e completed April 20, 2026, 10:56 p.m.
NED1 Entity disambiguation (via context triple) batch_6a08c59354388190b5c2a0c1bdd14575 completed May 16, 2026, 7:29 p.m.
NEDg Description generation batch_6a08c648e35881908c480b0afa383422 completed May 16, 2026, 7:32 p.m.
NED2 Entity disambiguation (via description) batch_6a08c6c6f9608190bdbcdd58f6b14008 completed May 16, 2026, 7:34 p.m.
Created at: April 16, 2026, 11:43 a.m.