Triple

T23377967
Position Surface form Disambiguated ID Type / Status
Subject King & Spalding E593657 entity
Predicate hasOfficeIn P1268 FINISHED
Object Riyadh, Saudi Arabia NE NERFINISHED

How this triple was built (2 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: Riyadh, Saudi Arabia | Statement: [King & Spalding, hasOfficeIn, Riyadh, Saudi Arabia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Riyadh, Saudi Arabia
Context triple: [King & Spalding, hasOfficeIn, Riyadh, Saudi Arabia]
  • A. Riyad
    Riyad is the given name of Algerian professional footballer Riyad Mahrez, a prominent winger known for his time at Leicester City and Manchester City.
  • B. Riyadh chosen
    Riyadh is the capital and largest city of Saudi Arabia, serving as a major political, economic, and cultural center in the Arab world.
  • C. Buraidah, Saudi Arabia
    Buraidah is the capital city of Saudi Arabia’s Al-Qassim Region, known as an agricultural hub and home to the football club Al Taawoun FC.
  • D. Dammam
    Dammam is a major Saudi Arabian city and commercial hub on the eastern coast, serving as a key center for the country’s oil industry and maritime trade.
  • E. Diriyah
    Diriyah is a historic town in Saudi Arabia that served as the original home of the Saudi royal family and the capital of the first Saudi state.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e25d268a50819095f2fd479da8ef3f completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f1a3b526ec8190b0304c72a9010abb completed April 29, 2026, 6:22 a.m.
Created at: April 17, 2026, 5:33 p.m.