Triple

T8398386
Position Surface form Disambiguated ID Type / Status
Subject British Resident in Perak E198109 entity
Predicate officeHolder P537 FINISHED
Object Hugh Low E361678 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: Hugh Low | Statement: [British Resident in Perak, officeHolder, Hugh Low]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hugh Low
Context triple: [British Resident in Perak, officeHolder, Hugh Low]
  • A. Hugh Low chosen
    Hugh Low was a 19th-century British colonial administrator and naturalist best known for leading the first recorded ascent of Mount Kinabalu in Borneo.
  • B. Cecil Brown
    Cecil Brown is a name shared by several notable individuals, including an American novelist and academic, a World War II war correspondent, and a British politician.
  • C. Russell Hill
    Russell Hill is a locality in Canberra, Australia, situated close to the parliamentary precinct of Capital Hill.
  • D. Nigel Lane
    Nigel Lane is a relatively obscure individual whose primary public mention appears to be as a namesake in reference data, with no widely documented achievements or roles.
  • E. Thomas Lownds
    Thomas Lownds was an 18th-century London publisher best known for issuing the first edition of Horace Walpole’s pioneering Gothic novel "The Castle of Otranto."
  • 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.