Triple

T15600523
Position Surface form Disambiguated ID Type / Status
Subject John Carpenter E375016 entity
Predicate directed P7373 FINISHED
Object Christine
Christine is a 1983 horror film, based on Stephen King’s novel, about a possessed Plymouth Fury with a deadly influence on its teenage owner.
E1167363 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: Christine | Statement: [John Carpenter, directed, Christine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Christine
Context triple: [John Carpenter, directed, Christine]
  • A. Christine
    Christine is a feminine given name of Greek origin meaning "follower of Christ," widely used in many Western countries.
  • B. Christine
    "Christine" is a 1980 post-punk/gothic rock single by Siouxsie and the Banshees, noted for its dark, atmospheric sound and psychologically themed lyrics.
  • C. Christine
    Christine is a horror novel by Stephen King about a possessed 1958 Plymouth Fury that exerts a deadly influence over its owner.
  • D. Christine
    Christine is a rival character to Heed, likely portrayed as a competitive or antagonistic counterpart in their shared narrative.
  • E. Christine
    Christine is a fictional character from the 1951 British drama film "Journey into Light."
  • 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: Christine
Triple: [John Carpenter, directed, Christine]
Generated description
Christine is a 1983 horror film, based on Stephen King’s novel, about a possessed Plymouth Fury with a deadly influence on its teenage owner.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Christine
Target entity description: Christine is a 1983 horror film, based on Stephen King’s novel, about a possessed Plymouth Fury with a deadly influence on its teenage owner.
  • A. Christine chosen
    Christine is a 1983 horror film directed by John Carpenter about a possessed, malevolent 1958 Plymouth Fury.
  • B. Christine
    Christine is a horror novel by Stephen King about a possessed 1958 Plymouth Fury that exerts a deadly influence over its owner.
  • C. Christine
    "Christine" is a 1980 post-punk/gothic rock single by Siouxsie and the Banshees, noted for its dark, atmospheric sound and psychologically themed lyrics.
  • D. Christine
    Christine is the protagonist of H. P. Lovecraft’s novel "Love," around whom the story’s emotional and psychological developments revolve.
  • E. Christine
    Christine is a central character in the 1973 mystery film "The Last of Sheila," around whom key elements of the movie’s intricate whodunit plot revolve.
  • F. None of above.

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_69d85cce25008190b13b52745fbd719b completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04e621fc4819097e8e85e7ddfdc6c completed April 16, 2026, 2:50 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff5f355ff48190a2c2c262c09e6de0 completed May 9, 2026, 4:22 p.m.
NEDg Description generation batch_69ff603299cc8190ad0eb57d10079651 completed May 9, 2026, 4:26 p.m.
NED2 Entity disambiguation (via description) batch_69ff60c6b7e48190a04cb43dcc3bdb39 completed May 9, 2026, 4:28 p.m.
Created at: April 10, 2026, 4:12 a.m.