Triple

T5000598
Position Surface form Disambiguated ID Type / Status
Subject Lilaea E112361 entity
Predicate near P350 FINISHED
Object Delphi (regionally) E393440 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: Delphi (regionally) | Statement: [Lilaea, near, Delphi (regionally)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Delphi (regionally)
Context triple: [Lilaea, near, Delphi (regionally)]
  • A. Delphi region chosen
    The Delphi region is an area of central Greece surrounding the ancient sanctuary and oracle of Delphi, a major religious and cultural center of the classical Greek world.
  • B. Chersonese
    Chersonese is an ancient Greek colony and later Roman-Byzantine city on the Crimean Peninsula, renowned for its well-preserved archaeological remains and historical significance in the Black Sea region.
  • C. Serdica
    Serdica was an important ancient Roman city in the province of Thracia, located on the site of present-day Sofia, Bulgaria.
  • D. Stolica
    Stolica is the highest peak of the Slovak Ore Mountains in central Slovakia, known for its forested slopes and scenic hiking routes.
  • E. Lefortovo
    Lefortovo is a Moscow Metro station on the Big Circle Line serving the historic Lefortovo district of Russia’s capital.
  • 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_69bd4432b32c81909f3b3c6bd10f0653 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd72bd90948190bf6ca21237402949 completed March 20, 2026, 4:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69be8a3a5a108190a028920b1ae0be7a completed March 21, 2026, 12:08 p.m.
Created at: March 20, 2026, 1:34 p.m.