Triple

T18975598
Position Surface form Disambiguated ID Type / Status
Subject The Brides of Dracula E464285 entity
Predicate stars P1956 FINISHED
Object David Peel
David Peel was a British actor best known for his role as the aristocratic vampire Baron Meinster in Hammer Films' 1960 horror movie "The Brides of Dracula."
E1352771 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: David Peel | Statement: [The Brides of Dracula, stars, David Peel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: David Peel
Context triple: [The Brides of Dracula, stars, David Peel]
  • A. Paul De Lisle
    Paul De Lisle is a Canadian musician best known as the longtime bassist for the rock band Smash Mouth.
  • B. David Daniel
    David Daniel is a cinematographer best known for his work on the dance film "You Got Served."
  • C. David Pack
    David Pack is an American musician, singer-songwriter, and producer best known as the co-founder and lead vocalist of the soft rock band Ambrosia.
  • D. Nigel Dodds
    Nigel Dodds is a Northern Irish Democratic Unionist Party politician who served as Deputy Leader of the DUP and as Member of Parliament for Belfast North.
  • E. Joe Pendry
    Joe Pendry is an American football coach and executive known for his extensive career as an offensive coordinator and front-office leader in both college football and the NFL.
  • 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: David Peel
Triple: [The Brides of Dracula, stars, David Peel]
Generated description
David Peel was a British actor best known for his role as the aristocratic vampire Baron Meinster in Hammer Films' 1960 horror movie "The Brides of Dracula."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: David Peel
Target entity description: David Peel was a British actor best known for his role as the aristocratic vampire Baron Meinster in Hammer Films' 1960 horror movie "The Brides of Dracula."
  • A. Paul De Lisle
    Paul De Lisle is a Canadian musician best known as the longtime bassist for the rock band Smash Mouth.
  • B. David Daniel
    David Daniel is a cinematographer best known for his work on the dance film "You Got Served."
  • C. David Pack
    David Pack is an American musician, singer-songwriter, and producer best known as the co-founder and lead vocalist of the soft rock band Ambrosia.
  • D. Nigel Dodds
    Nigel Dodds is a Northern Irish Democratic Unionist Party politician who served as Deputy Leader of the DUP and as Member of Parliament for Belfast North.
  • E. Joe Pendry
    Joe Pendry is an American football coach and executive known for his extensive career as an offensive coordinator and front-office leader in both college football and the NFL.
  • 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_69d8dd008af48190a97ff1c6488edf1b completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d61e71988190817cada25672a1ce completed April 20, 2026, 7:30 a.m.
NED1 Entity disambiguation (via context triple) batch_6a05ad3da2a881908488f18f35a34428 completed May 14, 2026, 11:08 a.m.
NEDg Description generation batch_6a05af056a0c8190969f3b7a371aa453 completed May 14, 2026, 11:16 a.m.
NED2 Entity disambiguation (via description) batch_6a05afb1c02481909018f47be226f486 completed May 14, 2026, 11:19 a.m.
Created at: April 10, 2026, noon