Triple

T19023870
Position Surface form Disambiguated ID Type / Status
Subject Tun E465556 entity
Predicate conferredBy P11 FINISHED
Object King of Malaysia 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: King of Malaysia | Statement: [Tun, conferredBy, King of Malaysia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: King of Malaysia
Context triple: [Tun, conferredBy, King of Malaysia]
  • A. King of Malaysia chosen
    The King of Malaysia is the constitutional monarch and ceremonial head of state elected from among the hereditary rulers of the Malay states.
  • B. Sultan of Johor
    The Sultan of Johor is the hereditary monarch and highest-ranking royal authority of the Malaysian state of Johor, traditionally wielding significant political and cultural influence.
  • C. Sultan of Selangor
    The Sultan of Selangor is the hereditary constitutional monarch of the Malaysian state of Selangor, serving as its highest ceremonial and religious authority.
  • D. Sultan of Kedah
    The Sultan of Kedah is the hereditary monarch and traditional ruler of the Malaysian state of Kedah, serving as its highest ceremonial and symbolic authority.
  • E. King of Malaya
    The King of Malaya was the constitutional monarch and head of state of the Federation of Malaya prior to the formation of Malaysia in 1963.
  • 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_69d8dd025c188190a1d81f5b4ec7e2c6 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d6e166088190937ef19739437f7c completed April 20, 2026, 7:33 a.m.
Created at: April 10, 2026, 12:02 p.m.