Triple

T17274449
Position Surface form Disambiguated ID Type / Status
Subject Sheila Dikshit E419350 entity
Predicate familyName P18 FINISHED
Object Dikshit
Dikshit is an Indian surname most prominently associated with the late politician Sheila Dikshit, a long-serving Chief Minister of Delhi.
 E1260708 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: Dikshit | Statement: [Sheila Dikshit, familyName, Dikshit]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Dikshit
Context triple: [Sheila Dikshit, familyName, Dikshit]
  • A. Sudarshan
    Sudarshan is a common Indian surname found across various regions and communities in India.
  • B. Nandiraj
    Nandiraj is a tributary river that feeds into the Indravati River in central India.
  • C. Srikanta
    Srikanta is a classic Bengali novel by Sarat Chandra Chattopadhyay that explores the emotional and social struggles of its introspective protagonist against the backdrop of early 20th-century Bengal.
  • D. Shankhodhar
    Shankhodhar is an island off the coast of Gujarat, India, revered as the mythological residence of Lord Krishna and a significant Hindu pilgrimage site.
  • E. Bhimsagar
    Bhimsagar is a notable historical site in Rajasthan, India, recognized for its heritage significance within the Jhalawar region.
  • 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: Dikshit
Triple: [Sheila Dikshit, familyName, Dikshit]
Generated description
Dikshit is an Indian surname most prominently associated with the late politician Sheila Dikshit, a long-serving Chief Minister of Delhi.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Dikshit
Target entity description: Dikshit is an Indian surname most prominently associated with the late politician Sheila Dikshit, a long-serving Chief Minister of Delhi.
  • A. Sudarshan
    Sudarshan is a common Indian surname found across various regions and communities in India.
  • B. Nandiraj
    Nandiraj is a tributary river that feeds into the Indravati River in central India.
  • C. Srikanta
    Srikanta is a classic Bengali novel by Sarat Chandra Chattopadhyay that explores the emotional and social struggles of its introspective protagonist against the backdrop of early 20th-century Bengal.
  • D. Shankhodhar
    Shankhodhar is an island off the coast of Gujarat, India, revered as the mythological residence of Lord Krishna and a significant Hindu pilgrimage site.
  • E. Bhimsagar
    Bhimsagar is a notable historical site in Rajasthan, India, recognized for its heritage significance within the Jhalawar region.
  • 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_69d886da626481908a14ce7830329a35 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e4332566c08190b4495dbbfe310ab6 completed April 19, 2026, 1:43 a.m.
NED1 Entity disambiguation (via context triple) batch_6a01794f6cf481909d76e3d61f9888c5 completed May 11, 2026, 6:38 a.m.
NEDg Description generation batch_6a017b5abdc481909832a6e46d21b34b completed May 11, 2026, 6:46 a.m.
NED2 Entity disambiguation (via description) batch_6a017bcf8a6081908922f5ef2673abae completed May 11, 2026, 6:48 a.m.
Created at: April 10, 2026, 5:40 a.m.