Triple

T8398354
Position Surface form Disambiguated ID Type / Status
Subject Sir Andrew Clarke E198108 entity
Predicate residence P75 FINISHED
Object Singapore E3670 NE FINISHED

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: Singapore | Statement: [Sir Andrew Clarke, residence, Singapore]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Singapore
Context triple: [Sir Andrew Clarke, residence, Singapore]
  • A. Singapore chosen
    Singapore is a sovereign city-state and island nation in Southeast Asia known for its global financial hub status, multicultural society, and highly developed, efficient infrastructure.
  • B. Singapore Bar
    The Singapore Bar is the professional body that regulates and represents qualified advocates and solicitors practicing law in Singapore.
  • C. Tuas, Singapore
    Tuas, Singapore is an industrial and port district at the western tip of Singapore, known for its heavy industries, container terminals, and land reclamation projects.
  • D. Nadi–Singapore
    Nadi–Singapore is an international flight route linking Nadi, Fiji with Singapore, serving as a key air corridor between the South Pacific and Southeast Asia.
  • E. Rochor, Singapore
    Rochor is a historic and centrally located planning area in Singapore known for its mix of traditional shophouses, cultural landmarks, and urban redevelopment.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69ca82f816bc8190ab321c07d72208c1 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb818a8dc081908efd5d7f910322e7 completed March 31, 2026, 8:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69cde86f6e148190812a8a9737310501 completed April 2, 2026, 3:54 a.m.
Created at: March 30, 2026, 6:04 p.m.