Triple

T14151731
Position Surface form Disambiguated ID Type / Status
Subject Sultaniyeh E350699 entity
Predicate partOf P40 FINISHED
Object Zanjan County E832531 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: Zanjan County | Statement: [Sultaniyeh, partOf, Zanjan County]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Zanjan County
Context triple: [Sultaniyeh, partOf, Zanjan County]
  • A. Zanjan County chosen
    Zanjan County is an administrative region in northwestern Iran that encompasses the city of Zanjan and surrounding areas within Zanjan Province.
  • B. Hamadan County
    Hamadan County is an administrative division in western Iran centered on the historic city of Hamadan, known for its cultural heritage and regional significance.
  • C. Qazvin County
    Qazvin County is an administrative division in Iran’s Qazvin Province, centered on the historic city of Qazvin and known for its cultural heritage and strategic location.
  • D. Karaj County
    Karaj County is an administrative division in Iran’s Alborz Province that includes the city of Karaj, a major urban and industrial center just west of Tehran.
  • E. Nahavand County
    Nahavand County is an administrative division in western Iran known for its historical significance and agricultural activities within Hamedan Province.
  • 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_69d8278775fc8190b0802d22ca2f495d completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de6124e23481909e5132a40a1d8624 completed April 14, 2026, 3:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcf7ea34408190830263d7f5a88ce9 completed May 7, 2026, 8:36 p.m.
Created at: April 10, 2026, 12:57 a.m.