Triple

T14631011
Position Surface form Disambiguated ID Type / Status
Subject Very Bad Things E343476 entity
Predicate castMember P1668 FINISHED
Object Russell B. McKenzie
Russell B. McKenzie is an actor known for appearing in the dark comedy crime film "Very Bad Things."
E1221768 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: Russell B. McKenzie | Statement: [Very Bad Things, castMember, Russell B. McKenzie]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Russell B. McKenzie
Context triple: [Very Bad Things, castMember, Russell B. McKenzie]
  • A. Russell O. Gillard
    Russell O. Gillard was the husband of silent film actress Lottie Pickford, sister of movie star Mary Pickford.
  • B. Vernon J. Mungo
    Vernon J. Mungo is a songwriter and music producer known for his work on tracks such as "Who Is She 2 U."
  • C. Donald C. MacPherson
    Donald C. MacPherson was the injured consumer whose landmark lawsuit against Buick Motor Company helped establish modern product liability law in the United States.
  • D. James A. Brundage
    James A. Brundage is an American historian and legal scholar best known for his influential work on medieval canon law and the history of sexuality.
  • E. Donald R. McLennan
    Donald R. McLennan was an American insurance executive and entrepreneur best known as the co-founder of the global professional services firm Marsh & McLennan.
  • 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: Russell B. McKenzie
Triple: [Very Bad Things, castMember, Russell B. McKenzie]
Generated description
Russell B. McKenzie is an actor known for appearing in the dark comedy crime film "Very Bad Things."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Russell B. McKenzie
Target entity description: Russell B. McKenzie is an actor known for appearing in the dark comedy crime film "Very Bad Things."
  • A. Russell O. Gillard
    Russell O. Gillard was the husband of silent film actress Lottie Pickford, sister of movie star Mary Pickford.
  • B. Vernon J. Mungo
    Vernon J. Mungo is a songwriter and music producer known for his work on tracks such as "Who Is She 2 U."
  • C. Donald C. MacPherson
    Donald C. MacPherson was the injured consumer whose landmark lawsuit against Buick Motor Company helped establish modern product liability law in the United States.
  • D. James A. Brundage
    James A. Brundage is an American historian and legal scholar best known for his influential work on medieval canon law and the history of sexuality.
  • E. Donald R. McLennan
    Donald R. McLennan was an American insurance executive and entrepreneur best known as the co-founder of the global professional services firm Marsh & McLennan.
  • 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_69d822dffc3c8190aa173b90761bffda completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb4a912248190a3df7f821395c776 completed April 14, 2026, 9:42 p.m.
NED1 Entity disambiguation (via context triple) batch_6a006ec7a4748190822e66a756bc95b9 completed May 10, 2026, 11:40 a.m.
NEDg Description generation batch_6a006fa02870819083c1b25eb4c8ffad completed May 10, 2026, 11:44 a.m.
NED2 Entity disambiguation (via description) batch_6a0070aee0248190b3463b98a739d1ae completed May 10, 2026, 11:49 a.m.
Created at: April 10, 2026, 1:26 a.m.