Triple
T8940772
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paruthiveeran |
E212893
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Ganja Karuppu |
E749991
|
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: Ganja Karuppu | Statement: [Paruthiveeran, starring, Ganja Karuppu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ganja Karuppu Context triple: [Paruthiveeran, starring, Ganja Karuppu]
-
A.
Ganja Karuppu
chosen
Ganja Karuppu is an Indian actor and comedian known for his supporting and comic roles in Tamil cinema.
-
B.
Manjappada
Manjappada is a passionate supporters’ group of Kerala Blasters FC, renowned for its massive, vibrant fan base and intense football culture in Indian football.
-
C.
Ganja
Ganja is one of Azerbaijan’s largest and oldest cities, known as a historic cultural and economic center in the South Caucasus.
-
D.
Pillaiyar
Pillaiyar is a widely revered elephant-headed Hindu deity, especially in South India, worshipped as the remover of obstacles and patron of beginnings and wisdom.
-
E.
Pazhamudircholai
Pazhamudircholai is a revered Hindu hill temple in Tamil Nadu, India, celebrated as one of the six principal abodes (Arupadai Veedu) of the god Murugan (Kartikeya).
- 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_69ca839694c88190b324ffeb43d23b08 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc66b8b37c8190bce6e049de8cf732 |
completed | April 1, 2026, 12:28 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfc1efdea881908b2c264d1c39c6ec |
completed | April 3, 2026, 1:34 p.m. |
Created at: March 30, 2026, 6:58 p.m.