Triple
T10213057
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jodhaa Akbar |
E242376
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object |
Raza Murad
Raza Murad is an Indian character actor known for his deep voice and frequent portrayals of villains and authoritative figures in Hindi cinema.
|
E850380
|
NE FINISHED |
How this triple was built (4 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: Raza Murad | Statement: [Jodhaa Akbar, starring, Raza Murad]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Raza Murad Context triple: [Jodhaa Akbar, starring, Raza Murad]
-
A.
Hasan Bughra Khan
Hasan Bughra Khan was a prominent ruler of the Kara-Khanid dynasty, known for consolidating its power in Central Asia during the late 10th century.
-
B.
Pasha Qasim
Pasha Qasim was an Ottoman military leader and provincial governor whose legacy is notably marked by the mosque bearing his name in Pécs, Hungary.
-
C.
Gultekin Khan
Gultekin Khan is a Bangladeshi academic and the former wife of renowned writer and filmmaker Humayun Ahmed.
-
D.
Muhammad Miranshah
Muhammad Miranshah was a Timurid prince and son of Abu Sa'id Mirza who played a role in the dynastic politics of Central Asia in the 15th century.
-
E.
Mahmud
Mahmud is a masculine given name of Arabic origin commonly used in various Muslim-majority cultures.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Raza Murad Triple: [Jodhaa Akbar, starring, Raza Murad]
Generated description
Raza Murad is an Indian character actor known for his deep voice and frequent portrayals of villains and authoritative figures in Hindi cinema.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Raza Murad Target entity description: Raza Murad is an Indian character actor known for his deep voice and frequent portrayals of villains and authoritative figures in Hindi cinema.
-
A.
Hasan Bughra Khan
Hasan Bughra Khan was a prominent ruler of the Kara-Khanid dynasty, known for consolidating its power in Central Asia during the late 10th century.
-
B.
Pasha Qasim
Pasha Qasim was an Ottoman military leader and provincial governor whose legacy is notably marked by the mosque bearing his name in Pécs, Hungary.
-
C.
Gultekin Khan
Gultekin Khan is a Bangladeshi academic and the former wife of renowned writer and filmmaker Humayun Ahmed.
-
D.
Muhammad Miranshah
Muhammad Miranshah was a Timurid prince and son of Abu Sa'id Mirza who played a role in the dynastic politics of Central Asia in the 15th century.
-
E.
Mahmud
Mahmud is a masculine given name of Arabic origin commonly used in various Muslim-majority cultures.
- F. None of above. chosen
Provenance (5 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_69d381ae26c48190985abd0e25ee5d04 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d3aa24efc081909714d98943543283 |
completed | April 6, 2026, 12:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d6a7f6730081908b941eaeb6c00993 |
completed | April 8, 2026, 7:09 p.m. |
| NEDg | Description generation | batch_69d6ad94a6a881908d4c3b4408695d5b |
completed | April 8, 2026, 7:33 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69d6d02015bc8190a7041a7d725c8a1b |
completed | April 8, 2026, 10:01 p.m. |
Created at: April 6, 2026, 11:03 a.m.