Triple

T1548003
Position Surface form Disambiguated ID Type / Status
Subject Pala Empire E33022 entity
Predicate capital P234 FINISHED
Object Vikrampura
Vikrampura was an important historical city that served as a principal royal center of the medieval Indian Pala dynasty in eastern India.
 E188425 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: Vikrampura | Statement: [Pala Empire, capital, Vikrampura]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Vikrampura
Context triple: [Pala Empire, capital, Vikrampura]
  • A. Kanchrapara
    Kanchrapara is a town in the North 24 Parganas district of West Bengal, India, known historically for its railway workshop and suburban connectivity to Kolkata.
  • B. Jagdishpur
    Jagdishpur is a town in the Bhojpur district of Bihar, India, historically known as the ancestral estate of the 19th-century freedom fighter Kunwar Singh.
  • C. Kadamtala
    Kadamtala is a small settlement located on Middle Andaman Island in the Andaman and Nicobar Islands of India.
  • D. Dahod
    Dahod is a town in the Indian state of Gujarat, historically notable as the birthplace of the Mughal emperor Aurangzeb.
  • E. Diglipur
    Diglipur is a northern town in India's Andaman and Nicobar Islands known as a key regional hub and gateway to nearby natural attractions such as Saddle Peak and Ross and Smith Islands.
  • 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: Vikrampura
Triple: [Pala Empire, capital, Vikrampura]
Generated description
Vikrampura was an important historical city that served as a principal royal center of the medieval Indian Pala dynasty in eastern India.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Vikrampura
Target entity description: Vikrampura was an important historical city that served as a principal royal center of the medieval Indian Pala dynasty in eastern India.
  • A. Kanchrapara
    Kanchrapara is a town in the North 24 Parganas district of West Bengal, India, known historically for its railway workshop and suburban connectivity to Kolkata.
  • B. Jagdishpur
    Jagdishpur is a town in the Bhojpur district of Bihar, India, historically known as the ancestral estate of the 19th-century freedom fighter Kunwar Singh.
  • C. Kadamtala
    Kadamtala is a small settlement located on Middle Andaman Island in the Andaman and Nicobar Islands of India.
  • D. Dahod
    Dahod is a town in the Indian state of Gujarat, historically notable as the birthplace of the Mughal emperor Aurangzeb.
  • E. Diglipur
    Diglipur is a northern town in India's Andaman and Nicobar Islands known as a key regional hub and gateway to nearby natural attractions such as Saddle Peak and Ross and Smith Islands.
  • 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_69a885ee6db8819099502bc5ce8af881 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a90856642c81909d88a679eb265b10 completed March 5, 2026, 4:36 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad68079e448190b71c2cd194abeb86 completed March 8, 2026, 12:13 p.m.
NEDg Description generation batch_69ad68b5e934819086a8383b4f0b8ab5 completed March 8, 2026, 12:16 p.m.
NED2 Entity disambiguation (via description) batch_69ad691acb8481908687f640e9f632ea completed March 8, 2026, 12:18 p.m.
Created at: March 4, 2026, 7:26 p.m.