Triple

T474738
Position Surface form Disambiguated ID Type / Status
Subject London Eye E9035 entity
Predicate designedBy P184 FINISHED
Object David Marks
David Marks was a British architect best known as the co-designer of the London Eye and other major public structures.
 E97171 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 Marks | Statement: [London Eye, designedBy, David Marks]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: David Marks
Context triple: [London Eye, designedBy, David Marks]
  • A. Sean Marks
    Sean Marks is a former NBA player and basketball executive best known for serving as the general manager who led the Brooklyn Nets’ roster rebuild in the late 2010s.
  • B. William Nolan
    William Nolan is an editor known for his work on editions of classic adventure literature, including "The Mark of Zorro."
  • C. Andrew Dunn
    Andrew Dunn is a British cinematographer known for his work on numerous high-profile films and television productions.
  • D. David Simas
    David Simas is an American political strategist and former Obama White House official who serves as a top executive leader at the Obama Foundation.
  • E. Michael Filerman
    Michael Filerman was an American television producer best known for developing and producing popular prime-time soap operas during the 1970s and 1980s.
  • 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 Marks
Triple: [London Eye, designedBy, David Marks]
Generated description
David Marks was a British architect best known as the co-designer of the London Eye and other major public structures.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: David Marks
Target entity description: David Marks was a British architect best known as the co-designer of the London Eye and other major public structures.
  • A. Sean Marks
    Sean Marks is a former NBA player and basketball executive best known for serving as the general manager who led the Brooklyn Nets’ roster rebuild in the late 2010s.
  • B. William Nolan
    William Nolan is an editor known for his work on editions of classic adventure literature, including "The Mark of Zorro."
  • C. Andrew Dunn
    Andrew Dunn is a British cinematographer known for his work on numerous high-profile films and television productions.
  • D. David Simas
    David Simas is an American political strategist and former Obama White House official who serves as a top executive leader at the Obama Foundation.
  • E. Michael Filerman
    Michael Filerman was an American television producer best known for developing and producing popular prime-time soap operas during the 1970s and 1980s.
  • 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_69a2e7ff81708190b0507a24a997232c completed Feb. 28, 2026, 1:05 p.m.
NER Named-entity recognition batch_69a2f039f3d88190a7c93ecbf1bf5f58 completed Feb. 28, 2026, 1:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69a76d6571588190b1f328e7b10b627c completed March 3, 2026, 11:23 p.m.
NEDg Description generation batch_69a78ce2d3608190af4f38768b6ef95e completed March 4, 2026, 1:37 a.m.
NED2 Entity disambiguation (via description) batch_69a78d84ccd08190aaa86a0adbd993a0 completed March 4, 2026, 1:40 a.m.
Created at: Feb. 28, 2026, 1:12 p.m.