Triple
T8564818
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vijay |
E202777
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Vijay |
E202777
|
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: Vijay | Statement: [Vijay, name, Vijay]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vijay Context triple: [Vijay, name, Vijay]
-
A.
Vijay
chosen
Vijay is a leading Indian film actor and playback singer, predominantly known for his work in Tamil cinema and his massive fan following across South India.
-
B.
Prithviraj Kapoor
Prithviraj Kapoor was a pioneering Indian actor and theatre legend, regarded as one of the founding figures of Hindi cinema and the Kapoor film dynasty.
-
C.
Akshay Kumar
Akshay Kumar is a prominent Indian film actor and producer, known for his action and comedy roles in Bollywood and his long-running, commercially successful career.
-
D.
Ajith Kumar
Ajith Kumar is a prominent Indian film actor and racing driver best known for his leading roles in Tamil cinema and his massive fan following.
-
E.
Ajay Devgn
Ajay Devgn is a prominent Indian film actor, director, and producer known for his intense performances in Hindi cinema and his versatility across action, drama, and comedy roles.
- 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_69ca8327b0a881908606ff860713964d |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe9d11274819099cc33a21a993a1f |
completed | March 31, 2026, 3:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cf42459a048190a5c480f4a212607a |
completed | April 3, 2026, 4:29 a.m. |
Created at: March 30, 2026, 6:20 p.m.