Triple

T1575721
Position Surface form Disambiguated ID Type / Status
Subject Joseph Karo E33645 entity
Predicate residence P75 FINISHED
Object Nikopol E137760 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: Nikopol | Statement: [Joseph Karo, residence, Nikopol]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nikopol
Context triple: [Joseph Karo, residence, Nikopol]
  • A. Nikopol chosen
    Nikopol is a historic town on the Danube River in northern Bulgaria, known as a former Ottoman-era Jewish center where the renowned rabbi and legal scholar Yosef Karo once lived.
  • B. Nikopolis
    Nikopolis is an ancient city in Epirus, Greece, founded by the Roman emperor Augustus and known today for its extensive archaeological remains.
  • C. Chrysopolis
    Chrysopolis was an ancient town located on the Asian side of the Bosporus, opposite Byzantium (later Constantinople), known historically as a strategic crossing and military site.
  • D. Hadrianopolis
    Hadrianopolis was an important ancient Roman and Byzantine city in Thrace, later known as Edirne in modern-day Turkey.
  • E. Jassy
    Jassy is the surname of Andy Jassy, the American business executive and CEO of Amazon.
  • 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_69a885f27a4c8190a4622252cdf54c00 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a908d2cffc819090f3d5cbebae3307 completed March 5, 2026, 4:38 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad402b44688190b02e6d146f009854 completed March 8, 2026, 9:23 a.m.
Created at: March 4, 2026, 7:27 p.m.