Triple

T19386069
Position Surface form Disambiguated ID Type / Status
Subject Treasury building E484936 entity
Predicate locatedNear P294 FINISHED
Object Whitehall
Whitehall is a central London street and government district that houses many key UK administrative buildings and departments.
 E16070 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: Whitehall | Statement: [Treasury building, locatedNear, Whitehall]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Whitehall
Context triple: [Treasury building, locatedNear, Whitehall]
  • A. Whitehall
    Whitehall is a small town in upstate New York that serves as a regional rail stop and gateway between New York and Vermont.
  • B. Whitehall
    Whitehall is a grand Gilded Age mansion in Palm Beach, Florida, built by Henry Flagler and now preserved as the Flagler Museum.
  • C. Whitehall
    Whitehall is a suburban borough in Allegheny County, Pennsylvania, located just south of Pittsburgh.
  • D. Whitehall
    Whitehall is a small coastal settlement on the Orkney island of Stronsay in Scotland.
  • E. Whitehall
    Whitehall is a primarily residential suburb on the north side of Dublin, Ireland, known for its local schools, churches, and proximity to major routes into the city centre.
  • 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: Whitehall
Triple: [Treasury building, locatedNear, Whitehall]
Generated description
Whitehall is a central London street and government district that houses many key UK administrative buildings and departments.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Whitehall
Target entity description: Whitehall is a central London street and government district that houses many key UK administrative buildings and departments.
  • A. Whitehall chosen
    Whitehall is the central London district that serves as the administrative heart of the United Kingdom, housing many key government departments and ministries.
  • B. Whitehall
    Whitehall is a primarily residential suburb on the north side of Dublin, Ireland, known for its local schools, churches, and proximity to major routes into the city centre.
  • C. Whitehall
    Whitehall is a small coastal settlement on the Orkney island of Stronsay in Scotland.
  • D. Whitehall
    Whitehall is a suburban borough in Allegheny County, Pennsylvania, located just south of Pittsburgh.
  • E. Whitehall
    Whitehall is a small town in upstate New York that serves as a regional rail stop and gateway between New York and Vermont.
  • F. None of above.

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_69d8e8d460d88190abf0591c5c9d2b0c completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e61b40d1148190b4fcd9ad56aa6910 completed April 20, 2026, 12:25 p.m.
NED1 Entity disambiguation (via context triple) batch_6a072b82d6008190b26d95f4356afe5c completed May 15, 2026, 2:19 p.m.
NEDg Description generation batch_6a072c5c67d48190a393eef73abb8aba completed May 15, 2026, 2:23 p.m.
NED2 Entity disambiguation (via description) batch_6a072ccebb388190b48c181017d95290 completed May 15, 2026, 2:25 p.m.
Created at: April 10, 2026, 1:35 p.m.