Triple

T7022001
Position Surface form Disambiguated ID Type / Status
Subject Director of the Royal Institution E162847 entity
Predicate workLocation P7 FINISHED
Object Royal Institution building, London
The Royal Institution building in London is a historic scientific venue and research institution renowned for its pioneering experiments, public lectures, and contributions to the advancement of science since the early 19th century.
E637002 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: Royal Institution building, London | Statement: [Director of the Royal Institution, workLocation, Royal Institution building, London]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Royal Institution building, London
Context triple: [Director of the Royal Institution, workLocation, Royal Institution building, London]
  • A. Royal Institute
    The Royal Institute, officially the Royal Society of Thailand, is Thailand’s national academy responsible for advancing and standardizing knowledge in fields such as language, science, and the humanities.
  • B. Royal Observatory, Greenwich
    The Royal Observatory, Greenwich is a historic astronomical observatory in London best known as the location of the Prime Meridian and for its pivotal role in the development of modern navigation and timekeeping.
  • C. Thames House, London
    Thames House in London is a prominent government building best known as the headquarters of the United Kingdom’s domestic security and counter-intelligence agency, MI5.
  • D. Somerset House, London
    Somerset House in London is a grand 18th-century riverside complex renowned for its neoclassical design and its role as a major cultural and arts centre.
  • E. Royal United Services Institute building, London
    The Royal United Services Institute building in London is a historic, grand Edwardian structure designed by prominent British architect Sir Aston Webb to house the UK’s leading defence and security think tank.
  • 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: Royal Institution building, London
Triple: [Director of the Royal Institution, workLocation, Royal Institution building, London]
Generated description
The Royal Institution building in London is a historic scientific venue and research institution renowned for its pioneering experiments, public lectures, and contributions to the advancement of science since the early 19th century.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Royal Institution building, London
Target entity description: The Royal Institution building in London is a historic scientific venue and research institution renowned for its pioneering experiments, public lectures, and contributions to the advancement of science since the early 19th century.
  • A. Royal Institute
    The Royal Institute, officially the Royal Society of Thailand, is Thailand’s national academy responsible for advancing and standardizing knowledge in fields such as language, science, and the humanities.
  • B. Royal Observatory, Greenwich
    The Royal Observatory, Greenwich is a historic astronomical observatory in London best known as the location of the Prime Meridian and for its pivotal role in the development of modern navigation and timekeeping.
  • C. Thames House, London
    Thames House in London is a prominent government building best known as the headquarters of the United Kingdom’s domestic security and counter-intelligence agency, MI5.
  • D. Somerset House, London
    Somerset House in London is a grand 18th-century riverside complex renowned for its neoclassical design and its role as a major cultural and arts centre.
  • E. Royal United Services Institute building, London
    The Royal United Services Institute building in London is a historic, grand Edwardian structure designed by prominent British architect Sir Aston Webb to house the UK’s leading defence and security think tank.
  • 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_69c6885b26248190a857541e3d10e299 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6e1ec34a48190b64cafb94e2f8706 completed March 27, 2026, 8 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7757686bc819089f6749e43bbb89d completed March 28, 2026, 6:30 a.m.
NEDg Description generation batch_69c778f1b3508190b58bbec8877a6052 completed March 28, 2026, 6:45 a.m.
NED2 Entity disambiguation (via description) batch_69c779cad0188190a840be47d2af5b2b completed March 28, 2026, 6:48 a.m.
Created at: March 27, 2026, 2:35 p.m.