Triple

T474828
Position Surface form Disambiguated ID Type / Status
Subject David Steel E9037 entity
Predicate familyName P18 FINISHED
Object Steel
Steel is a Scottish Liberal Democrat politician who served as leader of the Liberal Party and was the first Presiding Officer of the Scottish Parliament.
 E59715 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: Steel | Statement: [David Steel, familyName, Steel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Steel
Context triple: [David Steel, familyName, Steel]
  • A. Copper
    Copper is one of the animal mascots created to represent and promote the 2002 Winter Olympics in Salt Lake City.
  • B. Bessemer process
    The Bessemer process was a revolutionary 19th-century method for mass-producing steel by blowing air through molten pig iron to remove impurities, dramatically lowering costs and enabling large-scale industrialization.
  • C. Bessemer
    Bessemer is a surname most notably associated with Sir Henry Bessemer, the English inventor who revolutionized steel production in the 19th century.
  • D. Chromium
    Chromium is an open-source web browser project that serves as the foundation for several major browsers, including Google Chrome.
  • E. Gold
    Gold was the codename for one of the five Allied landing beaches used by British forces during the D-Day invasion of Normandy in World War II.
  • 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: Steel
Triple: [David Steel, familyName, Steel]
Generated description
Steel is a Scottish Liberal Democrat politician who served as leader of the Liberal Party and was the first Presiding Officer of the Scottish Parliament.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Steel
Target entity description: Steel is a Scottish Liberal Democrat politician who served as leader of the Liberal Party and was the first Presiding Officer of the Scottish Parliament.
  • A. Copper
    Copper is one of the animal mascots created to represent and promote the 2002 Winter Olympics in Salt Lake City.
  • B. Bessemer process
    The Bessemer process was a revolutionary 19th-century method for mass-producing steel by blowing air through molten pig iron to remove impurities, dramatically lowering costs and enabling large-scale industrialization.
  • C. Bessemer
    Bessemer is a surname most notably associated with Sir Henry Bessemer, the English inventor who revolutionized steel production in the 19th century.
  • D. Chromium
    Chromium is an open-source web browser project that serves as the foundation for several major browsers, including Google Chrome.
  • E. Gold
    Gold was the codename for one of the five Allied landing beaches used by British forces during the D-Day invasion of Normandy in World War II.
  • 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_69a468010c10819090d325d6c3d6f50c completed March 1, 2026, 4:23 p.m.
NEDg Description generation batch_69a468b2515881908bc2beb93685f404 completed March 1, 2026, 4:26 p.m.
NED2 Entity disambiguation (via description) batch_69a46912b7f48190979fb2ebd8e027e9 completed March 1, 2026, 4:28 p.m.
Created at: Feb. 28, 2026, 1:12 p.m.