Triple

T15297157
Position Surface form Disambiguated ID Type / Status
Subject Extraction (2015 film) E365689 entity
Predicate director P255 FINISHED
Object Steven C. Miller
Steven C. Miller is an American film director known for his work in action and horror genre movies.
E1148127 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: Steven C. Miller | Statement: [Extraction (2015 film), director, Steven C. Miller]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Steven C. Miller
Context triple: [Extraction (2015 film), director, Steven C. Miller]
  • A. David R. Miller
    David R. Miller was a Maryland farmer whose property, including the Cornfield, became a focal point of intense combat during the American Civil War’s Battle of Antietam.
  • B. Neil Miller
    Neil Miller is a skeptical psychiatrist and the stepfather figure who provides comic tension and emotional contrast in the Christmas film "The Santa Clause."
  • C. Paul Miller
    Paul Miller is a film director known for his work on the 1997 comedy movie "The Pest."
  • D. Peter Miller
    Peter Miller is a scholar known for his collaborative work with sociologist Nikolas Rose, particularly in the fields of governmentality, social theory, and the sociology of accounting and management.
  • E. Peter Miller
    Peter Miller is the central protagonist of the thriller film "Dressed to Kill," around whom the movie’s suspenseful plot and psychological tension revolve.
  • 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: Steven C. Miller
Triple: [Extraction (2015 film), director, Steven C. Miller]
Generated description
Steven C. Miller is an American film director known for his work in action and horror genre movies.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Steven C. Miller
Target entity description: Steven C. Miller is an American film director known for his work in action and horror genre movies.
  • A. David R. Miller
    David R. Miller was a Maryland farmer whose property, including the Cornfield, became a focal point of intense combat during the American Civil War’s Battle of Antietam.
  • B. Neil Miller
    Neil Miller is a skeptical psychiatrist and the stepfather figure who provides comic tension and emotional contrast in the Christmas film "The Santa Clause."
  • C. Paul Miller
    Paul Miller is a film director known for his work on the 1997 comedy movie "The Pest."
  • D. Peter Miller
    Peter Miller is a scholar known for his collaborative work with sociologist Nikolas Rose, particularly in the fields of governmentality, social theory, and the sociology of accounting and management.
  • E. Peter Miller
    Peter Miller is the central protagonist of the thriller film "Dressed to Kill," around whom the movie’s suspenseful plot and psychological tension revolve.
  • 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_69d85a113ee881908e297a1d38dd79fa completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e036848c1881908fbaaae0216d6d27 completed April 16, 2026, 1:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69feef82f6d08190b809260dda247dfe completed May 9, 2026, 8:25 a.m.
NEDg Description generation batch_69fef08efec88190a66159ba39409ec9 completed May 9, 2026, 8:30 a.m.
NED2 Entity disambiguation (via description) batch_69fef1715c3081909bddb24688c810a7 completed May 9, 2026, 8:33 a.m.
Created at: April 10, 2026, 3:15 a.m.