Triple

T19789405
Position Surface form Disambiguated ID Type / Status
Subject Trapped Ashes E475368 entity
Predicate hasSegment P3574 FINISHED
Object Stanley’s Girlfriend
"Stanley’s Girlfriend" is a horror anthology segment centered on a mysterious, alluring woman whose presence brings unsettling and supernatural consequences.
 E1396205 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: Stanley’s Girlfriend | Statement: [Trapped Ashes, hasSegment, Stanley’s Girlfriend]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Stanley’s Girlfriend
Context triple: [Trapped Ashes, hasSegment, Stanley’s Girlfriend]
  • A. Stella
    Stella is a 1955 Greek drama film directed by Michael Cacoyannis, renowned for its tragic story of a fiercely independent woman and its iconic performance by Melina Mercouri.
  • B. Stella
    Stella is a locality in South Africa that serves as a junction point along the N14 national highway.
  • C. Stella
    Stella is the internal codename that Atari used for the Atari 2600 video game console during its development.
  • D. Stella
    "Stella" is a novel by British writer Neil Bartlett, known for its inventive narrative style and exploration of queer identity and performance.
  • E. Stella
    Stella is the surname of Frank Stella, a prominent American painter, sculptor, and printmaker known for his contributions to minimalism and abstract art.
  • 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: Stanley’s Girlfriend
Triple: [Trapped Ashes, hasSegment, Stanley’s Girlfriend]
Generated description
"Stanley’s Girlfriend" is a horror anthology segment centered on a mysterious, alluring woman whose presence brings unsettling and supernatural consequences.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Stanley’s Girlfriend
Target entity description: "Stanley’s Girlfriend" is a horror anthology segment centered on a mysterious, alluring woman whose presence brings unsettling and supernatural consequences.
  • A. Stella
    Stella is a 1955 Greek drama film directed by Michael Cacoyannis, renowned for its tragic story of a fiercely independent woman and its iconic performance by Melina Mercouri.
  • B. Stella
    Stella is a locality in South Africa that serves as a junction point along the N14 national highway.
  • C. Stella
    "Stella" is a novel by British writer Neil Bartlett, known for its inventive narrative style and exploration of queer identity and performance.
  • D. Stella
    Stella is the surname of Frank Stella, a prominent American painter, sculptor, and printmaker known for his contributions to minimalism and abstract art.
  • E. Stella
    Stella is the internal codename that Atari used for the Atari 2600 video game console during its development.
  • 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_69d8e51b014081908b263e167370529a completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6538ae5108190b80eb7de6f445f02 completed April 20, 2026, 4:25 p.m.
NED1 Entity disambiguation (via context triple) batch_6a07c4fdbf4c8190a9177e87b65fc965 completed May 16, 2026, 1:14 a.m.
NEDg Description generation batch_6a07c90c07a48190b0f23597124b5017 completed May 16, 2026, 1:31 a.m.
NED2 Entity disambiguation (via description) batch_6a07c97b33b481909e9b45b37cfe87b3 completed May 16, 2026, 1:33 a.m.
Created at: April 10, 2026, 1:49 p.m.