Triple
T18806639
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sunny Balwani |
E459892
|
entity |
| Predicate | nickname |
P55
|
FINISHED |
| Object | Sunny Balwani |
—
|
NE NERFINISHED |
How this triple was built (2 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: Sunny Balwani | Statement: [Sunny Balwani, nickname, Sunny Balwani]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sunny Balwani Context triple: [Sunny Balwani, nickname, Sunny Balwani]
-
A.
Sunny Balwani
chosen
Sunny Balwani is a former executive of the blood-testing startup Theranos, widely known for his role in the company’s massive fraud scandal alongside founder Elizabeth Holmes.
-
B.
Rohit Bansal
Rohit Bansal is an Indian entrepreneur best known as the co-founder of the e-commerce company Snapdeal.
-
C.
Sachin Bansal
Sachin Bansal is an Indian entrepreneur best known as the co-founder and former CEO of the e-commerce company Flipkart.
-
D.
Shiv Nadar
Shiv Nadar is an Indian industrialist and philanthropist best known for building HCL into a global IT powerhouse and for his extensive contributions to education through the Shiv Nadar Foundation.
-
E.
Nandan Nilekani
Nandan Nilekani is an Indian entrepreneur, co-founder of Infosys, and former chairman of the Unique Identification Authority of India (UIDAI), where he led the Aadhaar digital identity project.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8d398c7d4819091cb2f7e48948aeb |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e5a3d7f8d08190a3e02fab6dc40bb5 |
completed | April 20, 2026, 3:56 a.m. |
Created at: April 10, 2026, 11:53 a.m.