Triple
T14000126
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | IITM |
E336797
|
entity |
| Predicate | hasAlumni |
P51
|
FINISHED |
| Object | Kris Gopalakrishnan |
E1053387
|
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: Kris Gopalakrishnan | Statement: [IITM, hasAlumni, Kris Gopalakrishnan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kris Gopalakrishnan Context triple: [IITM, hasAlumni, Kris Gopalakrishnan]
-
A.
Kris Gopalakrishnan
chosen
Kris Gopalakrishnan is an Indian billionaire businessman and co-founder of Infosys, one of the country’s largest IT services companies.
-
B.
Arvind Neelakantan
Arvind Neelakantan is a researcher in artificial intelligence and machine learning known for his work on large language models and neural network architectures.
-
C.
Ravi K. Chandran
Ravi K. Chandran is an acclaimed Indian cinematographer known for his visually striking work across Hindi and Tamil cinema.
-
D.
Prashant Damle
Prashant Damle is a renowned Indian actor and comedian celebrated for his prolific work in Marathi theatre, television, and films.
-
E.
Raj Subramaniam
Raj Subramaniam is the President and Chief Executive Officer of FedEx Corporation, a leading global logistics and delivery services company.
- 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_69d81c645c5c8190b1fd16a285a1b78a |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2eb81b208190a961e49a02fa4140 |
completed | April 14, 2026, 12:10 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fbac9f1f6c8190af7ddac920661bd5 |
completed | May 6, 2026, 9:03 p.m. |
Created at: April 9, 2026, 10:19 p.m.