Triple

T12188000
Position Surface form Disambiguated ID Type / Status
Subject Midnight Express E290385 entity
Predicate starring P1507 FINISHED
Object Brad Davis
Brad Davis was an American actor best known for his intense, award-winning performance in the 1978 prison drama film "Midnight Express."
E973890 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: Brad Davis | Statement: [Midnight Express, starring, Brad Davis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Brad Davis
Context triple: [Midnight Express, starring, Brad Davis]
  • A. Brad Davis
    Brad Davis is an American musician best known as a member of the country rock band The Boxmasters.
  • B. Kevin Davis
    Kevin Davis is a Canadian municipal politician who serves as the mayor of Brantford, Ontario.
  • C. Scott Davis
    Scott Davis is an American figure skater who competed at the national and international level in the 1990s.
  • D. Allen Davis
    Allen Davis was an influential American football executive and longtime principal owner and general manager of the NFL’s Oakland/Los Angeles Raiders, known for his maverick leadership and “Just win, baby” philosophy.
  • E. Ryan Davis
    Ryan Davis is a Ruby developer best known for creating the Minitest testing framework.
  • 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: Brad Davis
Triple: [Midnight Express, starring, Brad Davis]
Generated description
Brad Davis was an American actor best known for his intense, award-winning performance in the 1978 prison drama film "Midnight Express."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Brad Davis
Target entity description: Brad Davis was an American actor best known for his intense, award-winning performance in the 1978 prison drama film "Midnight Express."
  • A. Brad Davis
    Brad Davis is an American musician best known as a member of the country rock band The Boxmasters.
  • B. Kevin Davis
    Kevin Davis is a Canadian municipal politician who serves as the mayor of Brantford, Ontario.
  • C. Scott Davis
    Scott Davis is an American figure skater who competed at the national and international level in the 1990s.
  • D. Allen Davis
    Allen Davis was an influential American football executive and longtime principal owner and general manager of the NFL’s Oakland/Los Angeles Raiders, known for his maverick leadership and “Just win, baby” philosophy.
  • E. Ryan Davis
    Ryan Davis is a Ruby developer best known for creating the Minitest testing framework.
  • 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_69d6ab64de5881908d56eb7a75c6cc69 completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d916012c2c819085824332ad60059e completed April 10, 2026, 3:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69f61e5289608190bded58513316b1e5 completed May 2, 2026, 3:54 p.m.
NEDg Description generation batch_69f61f5b107c819082094791fcf7c5f4 completed May 2, 2026, 3:59 p.m.
NED2 Entity disambiguation (via description) batch_69f62006afcc8190b8e3b55a5fd8eaca completed May 2, 2026, 4:02 p.m.
Created at: April 8, 2026, 9:50 p.m.