Triple

T4928447
Position Surface form Disambiguated ID Type / Status
Subject Vikram Pandit E110632 entity
Predicate spouse P13 FINISHED
Object Swati Pandit
Swati Pandit is an Indian-American figure best known as the wife of former Citigroup CEO Vikram Pandit.
E480925 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: Swati Pandit | Statement: [Vikram Pandit, spouse, Swati Pandit]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Swati Pandit
Context triple: [Vikram Pandit, spouse, Swati Pandit]
  • A. Reema Lagoo
    Reema Lagoo was a prominent Indian film, television, and theatre actress best known for playing iconic motherly roles in Hindi and Marathi cinema.
  • B. Persis Khambatta
    Persis Khambatta was an Indian model and actress best known internationally for her role as Lieutenant Ilia in "Star Trek: The Motion Picture."
  • C. Jyoti Bansal
    Jyoti Bansal is an Indian-American entrepreneur and technologist best known for founding the application performance management company AppDynamics, which was acquired by Cisco for billions of dollars.
  • D. Sandhini Agarwal
    Sandhini Agarwal is an AI researcher known for her work at OpenAI on safety, policy, and the development and deployment of large-scale models such as CLIP.
  • E. Palak Patel
    Palak Patel is a film producer known for working on major Hollywood fantasy and action films, including "Snow White and the Huntsman."
  • 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: Swati Pandit
Triple: [Vikram Pandit, spouse, Swati Pandit]
Generated description
Swati Pandit is an Indian-American figure best known as the wife of former Citigroup CEO Vikram Pandit.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Swati Pandit
Target entity description: Swati Pandit is an Indian-American figure best known as the wife of former Citigroup CEO Vikram Pandit.
  • A. Reema Lagoo
    Reema Lagoo was a prominent Indian film, television, and theatre actress best known for playing iconic motherly roles in Hindi and Marathi cinema.
  • B. Persis Khambatta
    Persis Khambatta was an Indian model and actress best known internationally for her role as Lieutenant Ilia in "Star Trek: The Motion Picture."
  • C. Jyoti Bansal
    Jyoti Bansal is an Indian-American entrepreneur and technologist best known for founding the application performance management company AppDynamics, which was acquired by Cisco for billions of dollars.
  • D. Sandhini Agarwal
    Sandhini Agarwal is an AI researcher known for her work at OpenAI on safety, policy, and the development and deployment of large-scale models such as CLIP.
  • E. Palak Patel
    Palak Patel is a film producer known for working on major Hollywood fantasy and action films, including "Snow White and the Huntsman."
  • 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_69bd4415190c8190817bee7ec9f9f944 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd7038c12c81908a793b4a8768c28a completed March 20, 2026, 4:05 p.m.
NED1 Entity disambiguation (via context triple) batch_69be77ac88148190a51fa2e9085d6897 completed March 21, 2026, 10:49 a.m.
NEDg Description generation batch_69be7847a378819081687ec783a8b862 completed March 21, 2026, 10:51 a.m.
NED2 Entity disambiguation (via description) batch_69be7915a26c81909b21a128daebf5b3 completed March 21, 2026, 10:55 a.m.
Created at: March 20, 2026, 1:30 p.m.