Triple

T1086393
Position Surface form Disambiguated ID Type / Status
Subject Lawrence of Arabia E24060 entity
Predicate cinematographer P1953 FINISHED
Object Freddie Young
Freddie Young was a renowned British cinematographer best known for his sweeping, visually stunning work on epic films such as "Lawrence of Arabia."
E141366 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: Freddie Young | Statement: [Lawrence of Arabia, cinematographer, Freddie Young]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Freddie Young
Context triple: [Lawrence of Arabia, cinematographer, Freddie Young]
  • A. Freddie O’Connell
    Freddie O’Connell is an American politician who serves as the mayor of Nashville, Tennessee.
  • B. Freddie Heerdegen
    Freddie Heerdegen is the son of American actress Christina Ricci and her former husband James Heerdegen.
  • C. Frederick Erroll
    Frederick Erroll was a British Conservative politician and businessman who held several senior government posts in the mid-20th century, later becoming a life peer as Baron Erroll of Hale.
  • D. Elliott Frost
    Elliott Frost was one of the children of renowned American poet Robert Frost.
  • E. Freddie
    Freddie is a common diminutive given name, typically used as a nickname for Alfred or similar names.
  • 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: Freddie Young
Triple: [Lawrence of Arabia, cinematographer, Freddie Young]
Generated description
Freddie Young was a renowned British cinematographer best known for his sweeping, visually stunning work on epic films such as "Lawrence of Arabia."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Freddie Young
Target entity description: Freddie Young was a renowned British cinematographer best known for his sweeping, visually stunning work on epic films such as "Lawrence of Arabia."
  • A. Freddie O’Connell
    Freddie O’Connell is an American politician who serves as the mayor of Nashville, Tennessee.
  • B. Freddie Heerdegen
    Freddie Heerdegen is the son of American actress Christina Ricci and her former husband James Heerdegen.
  • C. Frederick Erroll
    Frederick Erroll was a British Conservative politician and businessman who held several senior government posts in the mid-20th century, later becoming a life peer as Baron Erroll of Hale.
  • D. Elliott Frost
    Elliott Frost was one of the children of renowned American poet Robert Frost.
  • E. Freddie
    Freddie is a common diminutive given name, typically used as a nickname for Alfred or similar names.
  • 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_69a49404428c819092dcc9632f5f7b8b completed March 1, 2026, 7:31 p.m.
NER Named-entity recognition batch_69a4b963161081908a523c8d63871652 completed March 1, 2026, 10:10 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac89fd91208190ac962ec7059f716b completed March 7, 2026, 8:26 p.m.
NEDg Description generation batch_69ac8becbbe48190a12b3814982c5c8f completed March 7, 2026, 8:34 p.m.
NED2 Entity disambiguation (via description) batch_69ac8c471754819096bcca9fea985a9f completed March 7, 2026, 8:36 p.m.
Created at: March 1, 2026, 7:42 p.m.