Triple

T6520034
Position Surface form Disambiguated ID Type / Status
Subject SNB E148356 entity
Predicate hasOfficeIn P1268 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: [SNB, hasOfficeIn, Singapore]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Singapore
Context triple: [SNB, hasOfficeIn, 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. 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.
  • D. 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.
  • E. Nanyang
    Nanyang is a major prefecture-level city in southwestern Henan Province, China, known for its long history, cultural heritage, and role as a regional economic and transportation hub.
  • 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_69c687e68e748190baceb9298f32d3ed completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c6ad92c624819086dbb12b4f6b78d3 completed March 27, 2026, 4:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6d51da9148190a82ff0885fd6548d completed March 27, 2026, 7:06 p.m.
Created at: March 27, 2026, 1:45 p.m.