Triple
T19191432
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Anant Ambani |
E469847
|
entity |
| Predicate | partner |
P1136
|
FINISHED |
| Object | Radhika Merchant |
—
|
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: Radhika Merchant | Statement: [Anant Ambani, partner, Radhika Merchant]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Radhika Merchant Context triple: [Anant Ambani, partner, Radhika Merchant]
-
A.
Radhika Merchant
chosen
Radhika Merchant is an Indian businesswoman and public figure known for her association with the Reliance Industries family and her high-profile marriage to Anant Ambani.
-
B.
Radhika Roy
Radhika Roy is an Indian media executive and co-founder of the news network NDTV.
-
C.
Sanah Kapur
Sanah Kapur is an Indian actress known for her supporting role in the film "Shaandaar" and for being part of the Kapur film family.
-
D.
Sobhita Dhulipala
Sobhita Dhulipala is an Indian actress and former model known for her work in Hindi cinema and streaming series such as "Made in Heaven."
-
E.
Bhumika Chawla
Bhumika Chawla is an Indian actress known for her work in Hindi, Telugu, and Tamil films, including notable roles in movies like "Tere Naam" and "Gandhi, My Father."
- 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_69d8dd0ad9088190a173b32657ae2e7a |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5f8a226dc8190a8a96960a4180298 |
completed | April 20, 2026, 9:57 a.m. |
Created at: April 10, 2026, 12:07 p.m.