Triple

T9228835
Position Surface form Disambiguated ID Type / Status
Subject Nag River E221759 entity
Predicate passesNear P416 FINISHED
Object Mahal
Mahal is a historic neighborhood in Nagpur, India, known as one of the city’s oldest and most culturally significant localities.
 E785129 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: Mahal | Statement: [Nag River, passesNear, Mahal]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mahal
Context triple: [Nag River, passesNear, Mahal]
  • A. Mahal
    Mahal is a landmark 1949 Indian Hindi-language psychological horror film, celebrated for pioneering the Bollywood gothic romance genre and launching Madhubala to stardom.
  • B. Mahal
    Mahal is a royal title historically used in the Mughal Empire to denote a queen or high-ranking consort in the imperial harem.
  • C. Mabini
    Mabini is a coastal municipality in the province of Batangas in the Philippines, known for its diving spots and marine biodiversity.
  • D. Mahala
    Mahala is the given first name of Mahalia Jackson, the legendary American gospel singer known as the “Queen of Gospel.”
  • E. Luisita
    Luisita is a Spanish feminine given name, typically used as a diminutive or affectionate form of Luisa.
  • 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: Mahal
Triple: [Nag River, passesNear, Mahal]
Generated description
Mahal is a historic neighborhood in Nagpur, India, known as one of the city’s oldest and most culturally significant localities.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mahal
Target entity description: Mahal is a historic neighborhood in Nagpur, India, known as one of the city’s oldest and most culturally significant localities.
  • A. Mahal
    Mahal is a royal title historically used in the Mughal Empire to denote a queen or high-ranking consort in the imperial harem.
  • B. Mahal
    Mahal is a landmark 1949 Indian Hindi-language psychological horror film, celebrated for pioneering the Bollywood gothic romance genre and launching Madhubala to stardom.
  • C. Mabini
    Mabini is a coastal municipality in the province of Batangas in the Philippines, known for its diving spots and marine biodiversity.
  • D. Mahala
    Mahala is the given first name of Mahalia Jackson, the legendary American gospel singer known as the “Queen of Gospel.”
  • E. Luisita
    Luisita is a Spanish feminine given name, typically used as a diminutive or affectionate form of Luisa.
  • 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_69ca83ec8db08190a9110df8232885d2 completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69ccdaa1c5b4819081dac6713053a8ae completed April 1, 2026, 8:43 a.m.
NED1 Entity disambiguation (via context triple) batch_69d0666364608190b104425819ccedf1 completed April 4, 2026, 1:16 a.m.
NEDg Description generation batch_69d06772c0508190883b22974ec09155 completed April 4, 2026, 1:20 a.m.
NED2 Entity disambiguation (via description) batch_69d067cab3a4819086a464f36a8adb3a completed April 4, 2026, 1:22 a.m.
Created at: March 30, 2026, 7:29 p.m.