Triple

T5926384
Position Surface form Disambiguated ID Type / Status
Subject Marathwada E131820 entity
Predicate hasMajorCity P316 FINISHED
Object Hingoli
Hingoli is a city in the Indian state of Maharashtra, known as an administrative and commercial center in the Marathwada region.
E569427 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: Hingoli | Statement: [Marathwada, hasMajorCity, Hingoli]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hingoli
Context triple: [Marathwada, hasMajorCity, Hingoli]
  • A. Buldhana
    Buldhana is a district in the Indian state of Maharashtra known for its Marathi-speaking population and use of the Varhadi dialect.
  • B. Sangli
    Sangli is a city in the Indian state of Maharashtra known for its fertile agricultural surroundings and prominence in sugar and turmeric production.
  • C. Ratnagiri
    Ratnagiri is a coastal city in Maharashtra, India, known for its Alphonso mangoes, historic forts, and scenic beaches along the Konkan coast.
  • D. Latur
    Latur is a city in the Marathwada region of western India known for its agricultural economy and for being the epicenter of a devastating earthquake in 1993.
  • E. Chandrapur
    Chandrapur is a district in the eastern part of Maharashtra, India, known for its coal mining industry, forests, and wildlife, including the Tadoba-Andhari Tiger Reserve.
  • 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: Hingoli
Triple: [Marathwada, hasMajorCity, Hingoli]
Generated description
Hingoli is a city in the Indian state of Maharashtra, known as an administrative and commercial center in the Marathwada region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Hingoli
Target entity description: Hingoli is a city in the Indian state of Maharashtra, known as an administrative and commercial center in the Marathwada region.
  • A. Buldhana
    Buldhana is a district in the Indian state of Maharashtra known for its Marathi-speaking population and use of the Varhadi dialect.
  • B. Sangli
    Sangli is a city in the Indian state of Maharashtra known for its fertile agricultural surroundings and prominence in sugar and turmeric production.
  • C. Ratnagiri
    Ratnagiri is a coastal city in Maharashtra, India, known for its Alphonso mangoes, historic forts, and scenic beaches along the Konkan coast.
  • D. Latur
    Latur is a city in the Marathwada region of western India known for its agricultural economy and for being the epicenter of a devastating earthquake in 1993.
  • E. Chandrapur
    Chandrapur is a district in the eastern part of Maharashtra, India, known for its coal mining industry, forests, and wildlife, including the Tadoba-Andhari Tiger Reserve.
  • 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_69c0085b75e88190a632f9691f9da48b completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c038542e548190b335df9a948c8490 completed March 22, 2026, 6:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69c124fda1848190894b51d45f2b0a7a completed March 23, 2026, 11:33 a.m.
NEDg Description generation batch_69c128c384008190b6c11709b2d2eee9 completed March 23, 2026, 11:49 a.m.
NED2 Entity disambiguation (via description) batch_69c129005930819095e2f4b296201611 completed March 23, 2026, 11:50 a.m.
Created at: March 22, 2026, 4 p.m.