Triple

T5696105
Position Surface form Disambiguated ID Type / Status
Subject Bukittinggi E125543 entity
Predicate formerName P65 FINISHED
Object Fort de Kock E155659 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: Fort de Kock | Statement: [Bukittinggi, formerName, Fort de Kock]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fort de Kock
Context triple: [Bukittinggi, formerName, Fort de Kock]
  • A. Fort de Kock chosen
    Fort de Kock is a former Dutch colonial garrison town in West Sumatra, Indonesia, now known as Bukittinggi, noted for its historical hilltop fort and role in Minangkabau history.
  • B. Graaff-Reinet
    Graaff-Reinet is a historic town in South Africa’s Eastern Cape, known as one of the country’s oldest settlements and a center of early Afrikaner history.
  • C. Colesberg
    Colesberg is a small historic town in South Africa’s Northern Cape, known as a key stopover on the N1 highway and a gateway to the semi-arid Karoo region.
  • D. Bothasig
    Bothasig is a residential suburb in the northern part of Cape Town, South Africa.
  • E. Mafeking
    Mafeking is a town in South Africa historically renowned as the site of the famous Siege of Mafeking during the Second Boer War.
  • 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_69c0082bb19c8190823a4facd3cba79b completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c0240bde1881909f7ea13bd84deaa8 completed March 22, 2026, 5:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69c05a5635448190ada625283405752f completed March 22, 2026, 9:08 p.m.
Created at: March 22, 2026, 3:45 p.m.