Triple

T15879839
Position Surface form Disambiguated ID Type / Status
Subject Narayan Rao E385046 entity
Predicate spouse P13 FINISHED
Object Gangabai
Gangabai was the wife of Narayan Rao, the Peshwa (prime minister) of the Maratha Empire in 18th-century India.
 E1071491 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: Gangabai | Statement: [Narayan Rao, spouse, Gangabai]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Gangabai
Context triple: [Narayan Rao, spouse, Gangabai]
  • A. Gangabai
    Gangabai was the mother of Madhav Rao II, a prominent Maratha Peshwa of the late 18th century.
  • B. Benipatti
    Benipatti is a town in the Madhubani district of the Indian state of Bihar, known for its rural setting and proximity to the region’s famed Mithila culture.
  • C. Viratnagar
    Viratnagar is a historic town in Rajasthan, India, known for its ancient Buddhist sites, rock-cut caves, and archaeological remains dating back to the Mauryan period.
  • D. Bhagyanagar
    Bhagyanagar is an old historical name for the Indian city now known as Hyderabad.
  • E. Radhanagar
    Radhanagar is a village in West Bengal, India, best known as the birthplace of the social reformer Raja Ram Mohan Roy.
  • 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: Gangabai
Triple: [Narayan Rao, spouse, Gangabai]
Generated description
Gangabai was the wife of Narayan Rao, the Peshwa (prime minister) of the Maratha Empire in 18th-century India.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Gangabai
Target entity description: Gangabai was the wife of Narayan Rao, the Peshwa (prime minister) of the Maratha Empire in 18th-century India.
  • A. Gangabai chosen
    Gangabai was the mother of Madhav Rao II, a prominent Maratha Peshwa of the late 18th century.
  • B. Benipatti
    Benipatti is a town in the Madhubani district of the Indian state of Bihar, known for its rural setting and proximity to the region’s famed Mithila culture.
  • C. Viratnagar
    Viratnagar is a historic town in Rajasthan, India, known for its ancient Buddhist sites, rock-cut caves, and archaeological remains dating back to the Mauryan period.
  • D. Bhagyanagar
    Bhagyanagar is an old historical name for the Indian city now known as Hyderabad.
  • E. Radhanagar
    Radhanagar is a village in West Bengal, India, best known as the birthplace of the social reformer Raja Ram Mohan Roy.
  • F. None of above.

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_69d86da4e86481909f1325fdc971b5ec completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e15600863c8190a2dbfd6d7ff495d7 completed April 16, 2026, 9:34 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffa9529ac48190993d1af234faea3b completed May 9, 2026, 9:38 p.m.
NEDg Description generation batch_69ffa9e9b17c8190b98d930fd5cb0723 completed May 9, 2026, 9:40 p.m.
NED2 Entity disambiguation (via description) batch_69ffaa973274819080889e1b9883b8dc completed May 9, 2026, 9:43 p.m.
Created at: April 10, 2026, 4:51 a.m.