Triple
T581667
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shantaram |
E15070
|
entity |
| Predicate | notableCharacter |
P1481
|
FINISHED |
| Object |
Prabaker
Prabaker is a cheerful and loyal Indian guide and friend who plays a central supporting role in Gregory David Roberts' novel "Shantaram."
|
E73350
|
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: Prabaker | Statement: [Shantaram, notableCharacter, Prabaker]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Prabaker Context triple: [Shantaram, notableCharacter, Prabaker]
-
A.
Premji
Premji is an Indian surname most prominently associated with billionaire philanthropist and Wipro chairman Azim Premji.
-
B.
Jagat Narayan
Jagat Narayan was an Indian educationist and public figure who served as a member of the British-era Hunter Commission on education reforms.
-
C.
Bhonsle
The Bhonsle were a prominent Maratha royal dynasty best known for producing Chhatrapati Shivaji, founder of the Maratha Empire in western India.
-
D.
Nathuram
Nathuram was the Indian nationalist and Hindu extremist who assassinated Mahatma Gandhi in 1948.
-
E.
Shadharwan
Shadharwan is the sloped stone base or foundation that runs along the lower exterior walls of the Kaaba in Mecca.
- 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: Prabaker Triple: [Shantaram, notableCharacter, Prabaker]
Generated description
Prabaker is a cheerful and loyal Indian guide and friend who plays a central supporting role in Gregory David Roberts' novel "Shantaram."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Prabaker Target entity description: Prabaker is a cheerful and loyal Indian guide and friend who plays a central supporting role in Gregory David Roberts' novel "Shantaram."
-
A.
Premji
Premji is an Indian surname most prominently associated with billionaire philanthropist and Wipro chairman Azim Premji.
-
B.
Jagat Narayan
Jagat Narayan was an Indian educationist and public figure who served as a member of the British-era Hunter Commission on education reforms.
-
C.
Bhonsle
The Bhonsle were a prominent Maratha royal dynasty best known for producing Chhatrapati Shivaji, founder of the Maratha Empire in western India.
-
D.
Nathuram
Nathuram was the Indian nationalist and Hindu extremist who assassinated Mahatma Gandhi in 1948.
-
E.
Shadharwan
Shadharwan is the sloped stone base or foundation that runs along the lower exterior walls of the Kaaba in Mecca.
- 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_69a4935783b8819082b77726ec10cc42 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a49b84899881909d5b2b4e67e22d9b |
completed | March 1, 2026, 8:03 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a50e23bce481908404040b848ba9c1 |
completed | March 2, 2026, 4:12 a.m. |
| NEDg | Description generation | batch_69a50ed652148190a84c0d2aa5307211 |
completed | March 2, 2026, 4:15 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69a50f53c16c8190bbeb7fa550ed46b1 |
completed | March 2, 2026, 4:17 a.m. |
Created at: March 1, 2026, 7:33 p.m.