Triple

T8535385
Position Surface form Disambiguated ID Type / Status
Subject Tushpa E202064 entity
Predicate modernSiteName P1213 FINISHED
Object Van Castle E734288 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: Van Castle | Statement: [Tushpa, modernSiteName, Van Castle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Van Castle
Context triple: [Tushpa, modernSiteName, Van Castle]
  • A. Van Castle chosen
    Van Castle is a historic fortress overlooking Lake Van in eastern Turkey, known for its ancient Urartian ruins and strategic hilltop location.
  • B. Bergville
    Bergville is a small town in KwaZulu-Natal, South Africa, serving as a gateway to the northern Drakensberg mountain region.
  • C. Osu Castle
    Osu Castle is a historic coastal fort and former seat of government in Accra, Ghana, notable for its colonial-era architecture and role in the transatlantic slave trade.
  • D. Hampoort
    Hampoort is a historic city gate, likely part of the old fortifications of a European town or city.
  • E. Memel Castle
    Memel Castle was a medieval Teutonic Order fortress located in what is now Klaipėda, Lithuania, serving as a key stronghold on the southeastern coast of the Baltic Sea.
  • 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_69ca832355b08190b8b6a4ab4a4a3554 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe6a295c88190a432a060ee73f04e completed March 31, 2026, 3:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce6d8332cc819083c86e0dc58bcc37 completed April 2, 2026, 1:22 p.m.
Created at: March 30, 2026, 6:17 p.m.