Triple

T9005951
Position Surface form Disambiguated ID Type / Status
Subject Kurdistan Province (Iran) E215143 entity
Predicate majorCity P316 FINISHED
Object Marivan
Marivan is a Kurdish-populated city in western Iran near the Iraqi border, known for its scenic Zarivar Lake and role as a regional commercial and cultural center.
 E800457 NE FINISHED

How this triple was built (4 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: Marivan | Statement: [Kurdistan Province (Iran), majorCity, Marivan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Marivan
Context triple: [Kurdistan Province (Iran), majorCity, Marivan]
  • A. Margilan
    Margilan is a historic city in eastern Uzbekistan renowned as a traditional center of silk production and trade along the Silk Road.
  • B. Ardabil
    Ardabil is a historic city in northwestern Iran known for its cultural heritage, including the UNESCO-listed Sheikh Safi al-Din Khānegāh and Shrine Ensemble.
  • C. Damghan
    Damghan is an ancient city in north-central Iran known for its historical monuments and archaeological sites, including one of the oldest mosques in the country.
  • D. Golestan
    Golestan is a settlement located within Baharestan County in Tehran Province, Iran.
  • E. Golestan
    Golestan is a classic 13th-century Persian literary work by Saadi that blends prose and poetry to convey moral lessons and social commentary.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Marivan
Triple: [Kurdistan Province (Iran), majorCity, Marivan]
Generated description
Marivan is a Kurdish-populated city in western Iran near the Iraqi border, known for its scenic Zarivar Lake and role as a regional commercial and cultural center.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Marivan
Target entity description: Marivan is a Kurdish-populated city in western Iran near the Iraqi border, known for its scenic Zarivar Lake and role as a regional commercial and cultural center.
  • A. Margilan
    Margilan is a historic city in eastern Uzbekistan renowned as a traditional center of silk production and trade along the Silk Road.
  • B. Ardabil
    Ardabil is a historic city in northwestern Iran known for its cultural heritage, including the UNESCO-listed Sheikh Safi al-Din Khānegāh and Shrine Ensemble.
  • C. Damghan
    Damghan is an ancient city in north-central Iran known for its historical monuments and archaeological sites, including one of the oldest mosques in the country.
  • D. Golestan
    Golestan is a settlement located within Baharestan County in Tehran Province, Iran.
  • E. Golestan
    Golestan is a classic 13th-century Persian literary work by Saadi that blends prose and poetry to convey moral lessons and social commentary.
  • F. None of above. chosen

Provenance (5 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_69ca83a12d648190b1e4fe11e8a31890 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc69bc6e208190b0c01e3761c04799 completed April 1, 2026, 12:41 a.m.
NED1 Entity disambiguation (via context triple) batch_69d121dce22881909484977629cc8a54 completed April 4, 2026, 2:36 p.m.
NEDg Description generation batch_69d1233a63d481908e322b7e86b5d124 completed April 4, 2026, 2:42 p.m.
NED2 Entity disambiguation (via description) batch_69d123d32c808190985da2639d2120f7 completed April 4, 2026, 2:44 p.m.
Created at: March 30, 2026, 7:05 p.m.