Triple

T8475122
Position Surface form Disambiguated ID Type / Status
Subject Solapur district E200370 entity
Predicate hasTown P847 FINISHED
Object Karmala
Karmala is a town in Maharashtra, India, known as a local administrative and commercial center within Solapur district.
E737867 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: Karmala | Statement: [Solapur district, hasTown, Karmala]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Karmala
Context triple: [Solapur district, hasTown, Karmala]
  • A. Nagole
    Nagole is a residential and commercial neighborhood in Hyderabad, India, served as a key terminus and transit hub on the Hyderabad Metro network.
  • B. Raichur
    Raichur is a historic city in the Indian state of Karnataka, known for its ancient forts, archaeological significance, and strategic location between major river systems.
  • C. Parbhani
    Parbhani is a significant city in the Marathwada region of Maharashtra, India, known as an important commercial and educational center.
  • D. Baramati
    Baramati is a town in the Pune district of Maharashtra, India, known as an agricultural and industrial hub with historical and political significance.
  • E. Khandala
    Khandala is a popular hill station in Maharashtra, India, known for its scenic valleys, waterfalls, and trekking spots in the Western Ghats.
  • 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: Karmala
Triple: [Solapur district, hasTown, Karmala]
Generated description
Karmala is a town in Maharashtra, India, known as a local administrative and commercial center within Solapur district.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Karmala
Target entity description: Karmala is a town in Maharashtra, India, known as a local administrative and commercial center within Solapur district.
  • A. Nagole
    Nagole is a residential and commercial neighborhood in Hyderabad, India, served as a key terminus and transit hub on the Hyderabad Metro network.
  • B. Raichur
    Raichur is a historic city in the Indian state of Karnataka, known for its ancient forts, archaeological significance, and strategic location between major river systems.
  • C. Parbhani
    Parbhani is a significant city in the Marathwada region of Maharashtra, India, known as an important commercial and educational center.
  • D. Baramati
    Baramati is a town in the Pune district of Maharashtra, India, known as an agricultural and industrial hub with historical and political significance.
  • E. Khandala
    Khandala is a popular hill station in Maharashtra, India, known for its scenic valleys, waterfalls, and trekking spots in the Western Ghats.
  • 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_69ca831a4f348190bfdd09250e86ae35 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe4f89e0081909e74beb7c8f55653 completed March 31, 2026, 3:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce4de1fae48190a1149f639faca147 completed April 2, 2026, 11:07 a.m.
NEDg Description generation batch_69ce4f587a7081908c357f82bc28a1aa completed April 2, 2026, 11:13 a.m.
NED2 Entity disambiguation (via description) batch_69ce5059e0f48190b8ff08253337f430 completed April 2, 2026, 11:17 a.m.
Created at: March 30, 2026, 6:11 p.m.