Triple
T16235760
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ketan Mehta |
E394105
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Sardar |
E277530
|
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: Sardar | Statement: [Ketan Mehta, notableWork, Sardar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sardar Context triple: [Ketan Mehta, notableWork, Sardar]
-
A.
Sardar
chosen
Sardar is a historical Indian honorific denoting a military or political leader, especially prominent among Maratha and other regional nobility.
-
B.
Kripalani
Kripalani is an Indian surname most prominently associated with J. B. Kripalani, a key leader in India’s independence movement and former president of the Indian National Congress.
-
C.
Quaid
Quaid is a surname most notably associated with the American acting family that includes Randy Quaid and his brother Dennis Quaid.
-
D.
Nandlal
Nandlal is an Indian given name, notably borne by Nandlal Nehru, an early 20th-century lawyer and member of the prominent Nehru family.
-
E.
Mamik Singh
Mamik Singh is an Indian actor best known for his role in the cult classic sports drama film "Jo Jeeta Wohi Sikandar."
- 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_69d87f204df88190a8f88923decf9835 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e2455abc608190ba3308c15c9e8a23 |
completed | April 17, 2026, 2:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0017ad3fa88190b71aa1e0c6414807 |
completed | May 10, 2026, 5:29 a.m. |
Created at: April 10, 2026, 5:04 a.m.