Triple
T13712170
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harpreet Banga |
E328799
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Harpreet Banga |
E328799
|
NE FINISHED |
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: Harpreet Banga | Statement: [Harpreet Banga, name, Harpreet Banga]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Harpreet Banga Context triple: [Harpreet Banga, name, Harpreet Banga]
-
A.
Harpreet Banga
chosen
Harpreet Banga is an individual notable enough to be recognized as a prominent bearer of the surname Banga.
-
B.
Manvinder Singh Banga
Manvinder Singh Banga is an Indian business executive best known for his long career at Unilever, where he rose to senior global leadership roles.
-
C.
Amandeep Singh
Amandeep Singh is an actor who appeared in the 2018 biographical thriller film "Hotel Mumbai."
-
D.
Amarjeet Sohi
Amarjeet Sohi is a Canadian politician who serves as the mayor of Edmonton and is a former federal cabinet minister.
-
E.
Balwinder Sandhu
Balwinder Sandhu is a former Indian cricketer best known for his crucial swing bowling and key lower-order runs in India's 1983 Cricket World Cup triumph.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d80770b9bc81909f70c8c317d53cff |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dd4395e8c0819098719c8cd344aa33 |
completed | April 13, 2026, 7:27 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7a845a29c81908096a785f5af5521 |
completed | May 3, 2026, 7:55 p.m. |
Created at: April 9, 2026, 9:54 p.m.