Triple

T19478599
Position Surface form Disambiguated ID Type / Status
Subject Names of Singapore E487318 entity
Predicate hasName P744 FINISHED
Object Temasek 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: Temasek | Statement: [Names of Singapore, hasName, Temasek]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Temasek
Context triple: [Names of Singapore, hasName, Temasek]
  • A. Sri Temasek
    Sri Temasek is the official residence of the Prime Minister of Singapore, located within the grounds of the Istana.
  • B. Temasek International
    Temasek International is the investment management arm of Singapore’s state-owned investment company Temasek Holdings, responsible for executing its global investment strategies.
  • C. Temasek Holdings chosen
    Temasek Holdings is a Singaporean state-owned investment company that manages a diversified global portfolio on behalf of the Singapore government.
  • D. OUE Limited
    OUE Limited is a Singapore-based diversified real estate company known for owning, developing, and managing commercial, hospitality, retail, and residential properties in Asia and beyond.
  • E. DBS Bank
    DBS Bank is a leading Singaporean multinational banking and financial services corporation, recognized as one of Asia’s largest and most prominent banks.
  • 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_69d8e8d924388190b847cb15bb3d0aff completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e63437b9748190a8fc6bf6b3d90918 completed April 20, 2026, 2:12 p.m.
Created at: April 10, 2026, 1:39 p.m.