Triple

T9925435
Position Surface form Disambiguated ID Type / Status
Subject Arak E187909 entity
Predicate formerName P65 FINISHED
Object Sultanabad
Sultanabad is the former name of the Iranian city now known as Arak, an important industrial and historical center in central Iran.
E829871 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: Sultanabad | Statement: [Arak, formerName, Sultanabad]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sultanabad
Context triple: [Arak, formerName, Sultanabad]
  • A. Mahmudabad
    Mahmudabad is a coastal city in northern Iran, situated along the Caspian Sea in Mazandaran Province and known for its beaches and tourism.
  • B. Nasirabad
    Nasirabad is a town and administrative area located in the Balochistan region of present-day Pakistan.
  • C. Shamshabad
    Shamshabad is a suburban area near Hyderabad in the Indian state of Telangana, known primarily for hosting the Rajiv Gandhi International Airport.
  • D. Mehmedabad
    Mehmedabad is a town in the Kheda district of Gujarat, India, known for its historical significance and location along key regional transport routes.
  • E. Asadabad
    Asadabad is a small but strategically important city in eastern Afghanistan, serving as the capital of Kunar Province near the Pakistani border.
  • 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: Sultanabad
Triple: [Arak, formerName, Sultanabad]
Generated description
Sultanabad is the former name of the Iranian city now known as Arak, an important industrial and historical center in central Iran.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sultanabad
Target entity description: Sultanabad is the former name of the Iranian city now known as Arak, an important industrial and historical center in central Iran.
  • A. Mahmudabad
    Mahmudabad is a coastal city in northern Iran, situated along the Caspian Sea in Mazandaran Province and known for its beaches and tourism.
  • B. Shamshabad
    Shamshabad is a suburban area near Hyderabad in the Indian state of Telangana, known primarily for hosting the Rajiv Gandhi International Airport.
  • C. Nasirabad
    Nasirabad is a town and administrative area located in the Balochistan region of present-day Pakistan.
  • D. Mehmedabad
    Mehmedabad is a town in the Kheda district of Gujarat, India, known for its historical significance and location along key regional transport routes.
  • E. Asadabad
    Asadabad is a small but strategically important city in eastern Afghanistan, serving as the capital of Kunar Province near the Pakistani border.
  • 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_69ca82b22a688190b52c75bd48429c10 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cdb599e32c8190ac676fa89c131bb6 completed April 2, 2026, 12:17 a.m.
NED1 Entity disambiguation (via context triple) batch_69d20e143660819097a9fa96365bc25a completed April 5, 2026, 7:24 a.m.
NEDg Description generation batch_69d21318b3008190af5db2bfb53bc2c6 completed April 5, 2026, 7:45 a.m.
NED2 Entity disambiguation (via description) batch_69d213b979e88190ad5a4f72784a0fe6 completed April 5, 2026, 7:48 a.m.
Created at: March 30, 2026, 8:43 p.m.