Triple
T19813398
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | T. R. Baalu |
E476001
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Thalikottai Raju |
—
|
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: Thalikottai Raju | Statement: [T. R. Baalu, givenName, Thalikottai Raju]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Thalikottai Raju Context triple: [T. R. Baalu, givenName, Thalikottai Raju]
-
A.
Kannasamy Nayaka
Kannasamy Nayaka, better known as Sri Vikrama Rajasinha, was the last king of the Kingdom of Kandy and the final native monarch of Sri Lanka before British colonial rule.
-
B.
Velupillai
Velupillai is a Tamil surname most prominently associated with Velupillai Prabhakaran, the founder and leader of the Liberation Tigers of Tamil Eelam (LTTE) in Sri Lanka.
-
C.
M. Sasikumar
M. Sasikumar is an Indian filmmaker and actor best known for his critically acclaimed Tamil film "Subramaniapuram," which he directed and starred in.
-
D.
T. R. Baalu
chosen
T. R. Baalu is an Indian politician from Tamil Nadu, known for his senior leadership roles in the Dravida Munnetra Kazhagam (DMK) and his tenure as a Union Minister.
-
E.
K. C. Vijayan
K. C. Vijayan is a Singaporean professional and alumnus of the prestigious Raffles Institution, likely recognized for notable contributions in his field.
- 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_69d8e51bc4208190a1c57d8c5d1b15e4 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6542d7c048190818359cbf430f50e |
completed | April 20, 2026, 4:28 p.m. |
Created at: April 10, 2026, 1:50 p.m.