Triple

T8120384
Position Surface form Disambiguated ID Type / Status
Subject Northern Iran E189591 entity
Predicate majorCity P316 FINISHED
Object Astara
Astara is a coastal city in northern Iran near the border with Azerbaijan, known as an important trade and transit hub on the Caspian Sea.
 E715119 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: Astara | Statement: [Northern Iran, majorCity, Astara]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Astara
Context triple: [Northern Iran, majorCity, Astara]
  • A. Ashgabat
    Ashgabat is the largest city and political, economic, and cultural center of Turkmenistan, known for its grand marble architecture and monumental cityscape.
  • B. Akçaabat
    Akçaabat is a coastal town and district in Turkey’s Trabzon Province on the Black Sea, known for its historic architecture and distinctive local cuisine.
  • C. Khujand
    Khujand is one of the oldest cities in Central Asia, a major urban center in northern Tajikistan known historically as a Silk Road hub on the Syr Darya River.
  • D. Karaganda
    Karaganda is a large industrial city in central Kazakhstan known for its coal mining industry and Soviet-era history.
  • E. Kizlyar
    Kizlyar is a town in the Republic of Dagestan, Russia, known historically as a frontier settlement and trading center in the North Caucasus region.
  • 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: Astara
Triple: [Northern Iran, majorCity, Astara]
Generated description
Astara is a coastal city in northern Iran near the border with Azerbaijan, known as an important trade and transit hub on the Caspian Sea.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Astara
Target entity description: Astara is a coastal city in northern Iran near the border with Azerbaijan, known as an important trade and transit hub on the Caspian Sea.
  • A. Ashgabat
    Ashgabat is the largest city and political, economic, and cultural center of Turkmenistan, known for its grand marble architecture and monumental cityscape.
  • B. Akçaabat
    Akçaabat is a coastal town and district in Turkey’s Trabzon Province on the Black Sea, known for its historic architecture and distinctive local cuisine.
  • C. Khujand
    Khujand is one of the oldest cities in Central Asia, a major urban center in northern Tajikistan known historically as a Silk Road hub on the Syr Darya River.
  • D. Karaganda
    Karaganda is a large industrial city in central Kazakhstan known for its coal mining industry and Soviet-era history.
  • E. Kizlyar
    Kizlyar is a town in the Republic of Dagestan, Russia, known historically as a frontier settlement and trading center in the North Caucasus region.
  • 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_69ca82bb74848190afb1f18640632c10 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb4359f3dc8190a2330cf6efb8c084 completed March 31, 2026, 3:45 a.m.
NED1 Entity disambiguation (via context triple) batch_69ccbeb0e12c8190863f7566d4c40953 completed April 1, 2026, 6:44 a.m.
NEDg Description generation batch_69ccc24c5684819093a4f58616122675 completed April 1, 2026, 6:59 a.m.
NED2 Entity disambiguation (via description) batch_69ccc38e85bc8190b0f4b2435a385f47 completed April 1, 2026, 7:04 a.m.
Created at: March 30, 2026, 5:33 p.m.