Triple

T173191
Position Surface form Disambiguated ID Type / Status
Subject High Society E3520 entity
Predicate starring P1507 FINISHED
Object John Lund
John Lund was an American film actor active in the 1940s and 1950s, known for his leading and supporting roles in Hollywood comedies and dramas.
 E26204 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: John Lund | Statement: [High Society, starring, John Lund]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: John Lund
Context triple: [High Society, starring, John Lund]
  • A. Peter Amundson
    Peter Amundson is a film editor best known for his work on major Hollywood productions, including the science-fiction action film "Pacific Rim."
  • B. Martin Lindauer
    Martin Lindauer was a German behavioral biologist and prominent honeybee researcher known for his pioneering work on insect communication and social organization.
  • C. Lars Jensen
    Lars Jensen is an entrepreneur best known as a co-founder of the online advertising technology company DoubleClick.
  • D. Jud Fry
    Jud Fry is the brooding, antagonistic farmhand and primary villain in the classic American musical "Oklahoma!".
  • E. Peder Sather
    Peder Sather was a 19th-century Norwegian-born American banker and philanthropist known for his significant financial support of the University of California, Berkeley.
  • 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: John Lund
Triple: [High Society, starring, John Lund]
Generated description
John Lund was an American film actor active in the 1940s and 1950s, known for his leading and supporting roles in Hollywood comedies and dramas.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: John Lund
Target entity description: John Lund was an American film actor active in the 1940s and 1950s, known for his leading and supporting roles in Hollywood comedies and dramas.
  • A. Peter Amundson
    Peter Amundson is a film editor best known for his work on major Hollywood productions, including the science-fiction action film "Pacific Rim."
  • B. Martin Lindauer
    Martin Lindauer was a German behavioral biologist and prominent honeybee researcher known for his pioneering work on insect communication and social organization.
  • C. Lars Jensen
    Lars Jensen is an entrepreneur best known as a co-founder of the online advertising technology company DoubleClick.
  • D. Jud Fry
    Jud Fry is the brooding, antagonistic farmhand and primary villain in the classic American musical "Oklahoma!".
  • E. Peder Sather
    Peder Sather was a 19th-century Norwegian-born American banker and philanthropist known for his significant financial support of the University of California, Berkeley.
  • 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_69a25374990081909766d30c79a18e0e completed Feb. 28, 2026, 2:31 a.m.
NER Named-entity recognition batch_69a258e1ec008190a89dd452f72574f4 completed Feb. 28, 2026, 2:54 a.m.
NED1 Entity disambiguation (via context triple) batch_69a32bc3efbc8190831cb527c122ac59 completed Feb. 28, 2026, 5:54 p.m.
NEDg Description generation batch_69a32d0fbc048190b01b3c2861c78ea3 completed Feb. 28, 2026, 5:59 p.m.
NED2 Entity disambiguation (via description) batch_69a32d5b05588190a67be5d0df28763f completed Feb. 28, 2026, 6 p.m.
Created at: Feb. 28, 2026, 2:39 a.m.