Triple
T5934131
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ArcelorMittal |
E132002
|
entity |
| Predicate | keyPerson |
P256
|
FINISHED |
| Object | Aditya Mittal |
E564015
|
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: Aditya Mittal | Statement: [ArcelorMittal, keyPerson, Aditya Mittal]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Aditya Mittal Context triple: [ArcelorMittal, keyPerson, Aditya Mittal]
-
A.
Aditya Mittal
chosen
Aditya Mittal is an Indian businessman and heir to the Mittal family who leads ArcelorMittal, one of the world’s largest steel and mining companies.
-
B.
Piyush Mishra
Piyush Mishra is an Indian actor, lyricist, singer, and theatre artist known for his intense performances and distinctive songwriting in Hindi cinema and theatre.
-
C.
Bhavish Aggarwal
Bhavish Aggarwal is an Indian entrepreneur best known for co-founding and leading the ride-hailing and mobility company Ola.
-
D.
Rahul Bhatia
Rahul Bhatia is an Indian businessman best known as the co-founder and key architect of IndiGo’s rise into India’s largest low-cost airline.
-
E.
Prashant Damle
Prashant Damle is a renowned Indian actor and comedian celebrated for his prolific work in Marathi theatre, television, and films.
- 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_69c0085c55dc8190aa90e242c956e2fa |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c0389f6fc881909527b928838ffcdd |
completed | March 22, 2026, 6:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c11cc81b3081908a35c4230eba3f06 |
completed | March 23, 2026, 10:58 a.m. |
Created at: March 22, 2026, 4 p.m.