Triple

T8684994
Position Surface form Disambiguated ID Type / Status
Subject The Mask of Dimitrios E206134 entity
Predicate mainCharacter P1183 FINISHED
Object Mr. Peters
Mr. Peters is a central figure in Eric Ambler’s espionage novel "The Mask of Dimitrios," around whom much of the mystery and intrigue unfolds.
 E751302 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: Mr. Peters | Statement: [The Mask of Dimitrios, mainCharacter, Mr. Peters]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mr. Peters
Context triple: [The Mask of Dimitrios, mainCharacter, Mr. Peters]
  • A. Mr. Peters
    Mr. Peters is a fictional character who appears in the work titled "Something New."
  • B. Mr. Harris
    Mr. Harris is the enslaver who legally owns and controls George Harris in the context of American slavery.
  • C. Mr. Hill
    Mr. Hill is the formal title used to address Marion Hill, likely in a professional or respectful social context.
  • D. Mr. Fletcher
    Mr. Fletcher is the video store owner in the comedy film "Be Kind Rewind," around whose struggling VHS rental shop the movie’s events and homemade remakes revolve.
  • E. Mr. Crocker
    Mr. Crocker is the paranoid, fairy-obsessed schoolteacher and primary antagonist in the animated series "The Fairly OddParents."
  • 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: Mr. Peters
Triple: [The Mask of Dimitrios, mainCharacter, Mr. Peters]
Generated description
Mr. Peters is a central figure in Eric Ambler’s espionage novel "The Mask of Dimitrios," around whom much of the mystery and intrigue unfolds.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mr. Peters
Target entity description: Mr. Peters is a central figure in Eric Ambler’s espionage novel "The Mask of Dimitrios," around whom much of the mystery and intrigue unfolds.
  • A. Mr. Peters
    Mr. Peters is a fictional character who appears in the work titled "Something New."
  • B. Mr. Harris
    Mr. Harris is the enslaver who legally owns and controls George Harris in the context of American slavery.
  • C. Mr. Hill
    Mr. Hill is the formal title used to address Marion Hill, likely in a professional or respectful social context.
  • D. Mr. Fletcher
    Mr. Fletcher is the video store owner in the comedy film "Be Kind Rewind," around whose struggling VHS rental shop the movie’s events and homemade remakes revolve.
  • E. Mr. Crocker
    Mr. Crocker is the paranoid, fairy-obsessed schoolteacher and primary antagonist in the animated series "The Fairly OddParents."
  • 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_69ca835379688190aa06b9d98e684d58 completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc4aeae740819099093906ccc5f640 completed March 31, 2026, 10:30 p.m.
NED1 Entity disambiguation (via context triple) batch_69cef3c3c74c81908cd9e881d5963492 completed April 2, 2026, 10:54 p.m.
NEDg Description generation batch_69cef521010081908815779c0bd2aac9 completed April 2, 2026, 11 p.m.
NED2 Entity disambiguation (via description) batch_69cef727ea088190bf40eaf5424ae864 completed April 2, 2026, 11:09 p.m.
Created at: March 30, 2026, 6:32 p.m.