Triple

T21844607
Position Surface form Disambiguated ID Type / Status
Subject Shumen E539342 entity
Predicate hasNearbySite P350 FINISHED
Object Madara Rider 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: Madara Rider | Statement: [Shumen, hasNearbySite, Madara Rider]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Madara Rider
Context triple: [Shumen, hasNearbySite, Madara Rider]
  • A. Madara Rider chosen
    Madara Rider is a medieval rock relief near the village of Madara in northeastern Bulgaria, depicting a horseman triumphing over a lion and recognized as a UNESCO World Heritage Site.
  • B. Kiz Rider
    Kiz Rider is a recurring Los Angeles police detective in Michael Connelly’s crime novels, known for her sharp investigative skills and partnership with Harry Bosch.
  • C. Hancate
    Hancate is a small village in the Dutch province of Overijssel, located within the municipality of Hellendoorn.
  • D. Megohime
    Megohime was a Japanese noblewoman of the late Sengoku and early Edo periods, best known as the politically significant wife of the powerful daimyo Date Masamune.
  • E. Maikaze
    Maikaze was an Imperial Japanese Navy destroyer of the Kagerō class that served during World War II, participating in various Pacific naval operations before being sunk in 1944.
  • 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_69e0c476c3c88190a92d08ebb59a128a completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69f0bd5248f08190ba208512eafbe7ad completed April 28, 2026, 1:59 p.m.
Created at: April 16, 2026, 6:55 p.m.