Triple

T3723614
Position Surface form Disambiguated ID Type / Status
Subject Baku E81696 entity
Predicate contains P35 FINISHED
Object Icherisheher
Icherisheher is the historic walled old town of Baku, Azerbaijan, known for its medieval architecture and UNESCO World Heritage status.
E384412 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: Icherisheher | Statement: [Baku, contains, Icherisheher]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Icherisheher
Context triple: [Baku, contains, Icherisheher]
  • A. Sarakhs
    Sarakhs is a historic border city in northeastern Iran, known for its strategic location along ancient trade routes between Iran and Central Asia.
  • B. Bakhchisaray
    Bakhchisaray is a historic town in Crimea known for its former role as the capital of the Crimean Khanate and its notable architectural and cultural heritage.
  • C. Urgench
    Urgench is a city in western Uzbekistan that serves as the administrative center of Khorezm Region and a gateway to the historic city of Khiva.
  • D. Buynaksk
    Buynaksk is a significant urban center in the Republic of Dagestan in southern Russia, known for its strategic location in the North Caucasus region.
  • E. Shuakhevi
    Shuakhevi is a small town and municipality in the mountainous region of Adjara in southwestern Georgia.
  • 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: Icherisheher
Triple: [Baku, contains, Icherisheher]
Generated description
Icherisheher is the historic walled old town of Baku, Azerbaijan, known for its medieval architecture and UNESCO World Heritage status.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Icherisheher
Target entity description: Icherisheher is the historic walled old town of Baku, Azerbaijan, known for its medieval architecture and UNESCO World Heritage status.
  • A. Sarakhs
    Sarakhs is a historic border city in northeastern Iran, known for its strategic location along ancient trade routes between Iran and Central Asia.
  • B. Bakhchisaray
    Bakhchisaray is a historic town in Crimea known for its former role as the capital of the Crimean Khanate and its notable architectural and cultural heritage.
  • C. Urgench
    Urgench is a city in western Uzbekistan that serves as the administrative center of Khorezm Region and a gateway to the historic city of Khiva.
  • D. Buynaksk
    Buynaksk is a significant urban center in the Republic of Dagestan in southern Russia, known for its strategic location in the North Caucasus region.
  • E. Shuakhevi
    Shuakhevi is a small town and municipality in the mountainous region of Adjara in southwestern Georgia.
  • 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_69ad8b1b7ef081908d2d381bbf54985a completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69adcaf3f2ec8190a3a8f363cfb762f3 completed March 8, 2026, 7:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4db0e40b08190abacdda42dbde411 completed March 14, 2026, 3:50 a.m.
NEDg Description generation batch_69b4dc80efe88190b837963691800d0c completed March 14, 2026, 3:56 a.m.
NED2 Entity disambiguation (via description) batch_69b4dce9f7f0819098aafe82c27ad851 completed March 14, 2026, 3:58 a.m.
Created at: March 8, 2026, 3:34 p.m.