Triple
T23506514
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gurbaksh Singh Dhillon |
E572294
|
entity |
| Predicate | hasSurname |
P18
|
FINISHED |
| Object | Dhillon |
—
|
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: Dhillon | Statement: [Gurbaksh Singh Dhillon, hasSurname, Dhillon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dhillon Context triple: [Gurbaksh Singh Dhillon, hasSurname, Dhillon]
-
A.
Dhillon
chosen
Dhillon is a common Punjabi surname associated with a prominent Jat clan found primarily in northern India and the Punjabi diaspora.
-
B.
Deep Dhillon
Deep Dhillon is an Indian film and television actor known for playing supporting and villainous roles in numerous Hindi movies and TV serials.
-
C.
Sandhu
Sandhu is a common Punjabi surname associated with a prominent Jat clan found mainly in northern India and Pakistan.
-
D.
Gurinder Singh Dhillon
Gurinder Singh Dhillon is an Indian spiritual leader best known as the head of the Radha Soami Satsang Beas, a large and influential spiritual organization based in Punjab.
-
E.
Kamaldeep
Kamaldeep is a cinematographer known for working on the film "Mamta."
- 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_69e245b5e4208190bac8a6509867e394 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1a9009ca081908c4cffb8c32293ec |
completed | April 29, 2026, 6:45 a.m. |
Created at: April 17, 2026, 6:07 p.m.