Triple

T2666170
Position Surface form Disambiguated ID Type / Status
Subject Martin Freeman E55639 entity
Predicate hasChild P369 FINISHED
Object Joe Freeman
Joe Freeman is the son of English actor Martin Freeman.
E293078 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: Joe Freeman | Statement: [Martin Freeman, hasChild, Joe Freeman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Joe Freeman
Context triple: [Martin Freeman, hasChild, Joe Freeman]
  • A. Max Mullen
    Max Mullen is an American entrepreneur best known as a co-founder of the grocery delivery company Instacart.
  • B. Larry Robinson
    Larry Robinson is an American academic and administrator best known for serving as president of Florida A&M University.
  • C. Larry Robinson
    Larry Robinson is a Hall of Fame Canadian ice hockey defenseman best known for his long, successful career with the Montreal Canadiens and multiple Stanley Cup championships.
  • D. John J. Haden
    John J. Haden was an early 20th-century Florida horticulturist best known for developing the influential Haden mango cultivar that helped launch Florida’s commercial mango industry.
  • E. Stuart Heisler
    Stuart Heisler was an American film and television director known for his work in Hollywood from the 1930s through the 1960s, including dramas, thrillers, and war films.
  • 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: Joe Freeman
Triple: [Martin Freeman, hasChild, Joe Freeman]
Generated description
Joe Freeman is the son of English actor Martin Freeman.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Joe Freeman
Target entity description: Joe Freeman is the son of English actor Martin Freeman.
  • A. Max Mullen
    Max Mullen is an American entrepreneur best known as a co-founder of the grocery delivery company Instacart.
  • B. Larry Robinson
    Larry Robinson is an American academic and administrator best known for serving as president of Florida A&M University.
  • C. Larry Robinson
    Larry Robinson is a Hall of Fame Canadian ice hockey defenseman best known for his long, successful career with the Montreal Canadiens and multiple Stanley Cup championships.
  • D. John J. Haden
    John J. Haden was an early 20th-century Florida horticulturist best known for developing the influential Haden mango cultivar that helped launch Florida’s commercial mango industry.
  • E. Stuart Heisler
    Stuart Heisler was an American film and television director known for his work in Hollywood from the 1930s through the 1960s, including dramas, thrillers, and war films.
  • 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_69ab49e54de48190be708cd1cf8be073 completed March 6, 2026, 9:40 p.m.
NER Named-entity recognition batch_69abd97040e48190b0a87489f108810e completed March 7, 2026, 7:53 a.m.
NED1 Entity disambiguation (via context triple) batch_69afb6775b008190a59e480516c3ef41 completed March 10, 2026, 6:13 a.m.
NEDg Description generation batch_69afb75ea498819089c79e63052e9696 completed March 10, 2026, 6:17 a.m.
NED2 Entity disambiguation (via description) batch_69afb83ba6dc8190931d691d3e354bd7 completed March 10, 2026, 6:20 a.m.
Created at: March 6, 2026, 9:54 p.m.