Triple

T5117569
Position Surface form Disambiguated ID Type / Status
Subject Arda River E115374 entity
Predicate nearCity P350 FINISHED
Object Edirne E19465 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: Edirne | Statement: [Arda River, nearCity, Edirne]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Edirne
Context triple: [Arda River, nearCity, Edirne]
  • A. Edirne chosen
    Edirne is a historic city in northwestern Turkey that served as an early capital of the Ottoman Empire and is renowned for its Ottoman-era architecture, including the Selimiye Mosque.
  • B. Ardahan
    Ardahan is a town in northeastern Turkey that serves as the capital of Ardahan Province near the border with Georgia.
  • C. Vidin
    Vidin is a historic city and river port in northwestern Bulgaria on the Danube, known for its medieval fortress and role as a regional center during the Second Bulgarian Empire.
  • D. Silistra
    Silistra is a historic city in northeastern Bulgaria on the Danube River, known as an important cultural and economic center of the Dobruja region.
  • E. Asenovgrad
    Asenovgrad is a town in southern Bulgaria known as a gateway to the Rhodope Mountains and a regional center rich in historical and religious landmarks.
  • 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_69bd4441d1648190a54a533895041987 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd77ccb19c8190844c628ff7cfcca2 completed March 20, 2026, 4:37 p.m.
NED1 Entity disambiguation (via context triple) batch_69bec3758bb4819082d5876c4dc9df8d completed March 21, 2026, 4:12 p.m.
Created at: March 20, 2026, 1:41 p.m.