Triple
T8564880
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Suriya |
E202778
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Karthi |
E743797
|
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: Karthi | Statement: [Suriya, sibling, Karthi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Karthi Context triple: [Suriya, sibling, Karthi]
-
A.
Karthi
chosen
Karthi is a popular Indian Tamil film actor known for his versatile performances in commercial and critically acclaimed movies.
-
B.
Sivakumar
Sivakumar is a veteran Indian Tamil film actor known for his work since the 1960s and as the father of popular actors Suriya and Karthi.
-
C.
Paruthiveeran
Paruthiveeran is a critically acclaimed 2007 Tamil rural drama film directed by Ameer and starring Karthi, noted for its realistic portrayal of village life and powerful performances.
-
D.
Karthik Bala
Karthik Bala is a video game developer and entrepreneur best known as the co-founder of the game studio Vicarious Visions.
-
E.
Sivakarthikeyan
Sivakarthikeyan is a popular Indian actor, producer, and playback singer known for his comedic and family-oriented roles primarily in Tamil cinema.
- 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_69cef3265be481909acfef718e2bd403 |
completed | April 2, 2026, 10:52 p.m. |
Created at: March 30, 2026, 6:20 p.m.