Triple
T19051726
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Adept AI |
E466275
|
entity |
| Predicate | foundedBy |
P104
|
FINISHED |
| Object | Niki Parmar |
—
|
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: Niki Parmar | Statement: [Adept AI, foundedBy, Niki Parmar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Niki Parmar Context triple: [Adept AI, foundedBy, Niki Parmar]
-
A.
Niki Parmar
chosen
Niki Parmar is a computer scientist and co-author of the seminal "Attention Is All You Need" paper that introduced the Transformer architecture in deep learning.
-
B.
Loveleen Tandan
Loveleen Tandan is an Indian film director and casting director best known for her co-directing work on the Academy Award–winning film "Slumdog Millionaire."
-
C.
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.
-
D.
Gita Patel
Gita Patel is the mother of Pi Patel, the protagonist of Yann Martel’s novel "Life of Pi," and is portrayed as a compassionate and grounding influence in his life.
-
E.
Sheila Karklin
Sheila Karklin is best known as the former wife of American political and social activist Abbie Hoffman.
- 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_69d8dd040fb881909af2a964f65ad208 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5dc031ff881908e8c68c7aaff3733 |
completed | April 20, 2026, 7:55 a.m. |
Created at: April 10, 2026, 12:03 p.m.