Triple

T13222012
Position Surface form Disambiguated ID Type / Status
Subject Tucker & Dale vs. Evil E314777 entity
Predicate cinematography P1953 FINISHED
Object David Geddes
David Geddes is a cinematographer known for his work on the horror-comedy film "Tucker & Dale vs. Evil."
E1040514 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 Geddes | Statement: [Tucker & Dale vs. Evil, cinematography, David Geddes]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: David Geddes
Context triple: [Tucker & Dale vs. Evil, cinematography, David Geddes]
  • A. Paul Duguid
    Paul Duguid is a scholar of information studies and co-author of the influential book "The Social Life of Information" with John Seely Brown.
  • B. David Lyall
    David Lyall was a 19th-century Scottish botanist and naturalist known for his extensive plant collections and contributions to the botanical exploration of New Zealand and the Antarctic regions.
  • C. David Semple
    David Semple was a British bacteriologist best known for developing an early anti-rabies vaccine while serving in the Indian Medical Service.
  • D. Andrew Sturgeon
    Andrew Sturgeon is a relatively obscure individual whose primary distinguishing feature is sharing the surname Sturgeon, with no widely documented public achievements or roles.
  • E. David Farquharson
    David Farquharson was an architect known for designing South Hall.
  • 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 Geddes
Triple: [Tucker & Dale vs. Evil, cinematography, David Geddes]
Generated description
David Geddes is a cinematographer known for his work on the horror-comedy film "Tucker & Dale vs. Evil."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: David Geddes
Target entity description: David Geddes is a cinematographer known for his work on the horror-comedy film "Tucker & Dale vs. Evil."
  • A. Paul Duguid
    Paul Duguid is a scholar of information studies and co-author of the influential book "The Social Life of Information" with John Seely Brown.
  • B. David Lyall
    David Lyall was a 19th-century Scottish botanist and naturalist known for his extensive plant collections and contributions to the botanical exploration of New Zealand and the Antarctic regions.
  • C. David Semple
    David Semple was a British bacteriologist best known for developing an early anti-rabies vaccine while serving in the Indian Medical Service.
  • D. Andrew Sturgeon
    Andrew Sturgeon is a relatively obscure individual whose primary distinguishing feature is sharing the surname Sturgeon, with no widely documented public achievements or roles.
  • E. David Farquharson
    David Farquharson was an architect known for designing South Hall.
  • 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_69d806affc688190a25b6ccc588e9c72 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d98cf74d708190a61d8ad938653b06 completed April 10, 2026, 11:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69f73973248481909ed29ea68955f447 completed May 3, 2026, 12:02 p.m.
NEDg Description generation batch_69f73b50408c8190a469ecc92b0cc582 completed May 3, 2026, 12:10 p.m.
NED2 Entity disambiguation (via description) batch_69f73bdb099c8190a90654709d33ccbf completed May 3, 2026, 12:13 p.m.
Created at: April 9, 2026, 9:18 p.m.