Triple
T7122369
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Feluda series |
E165977
|
entity |
| Predicate | hasWork |
P6260
|
FINISHED |
| Object |
Sonar Kella
Sonar Kella is a popular Bengali detective novel by Satyajit Ray featuring the sleuth Feluda, centered on a mystery involving a supposed past life and a legendary golden fortress in Rajasthan.
|
E643200
|
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: Sonar Kella | Statement: [Feluda series, hasWork, Sonar Kella]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sonar Kella Context triple: [Feluda series, hasWork, Sonar Kella]
-
A.
Kallen
Kallen is a surname most notably associated with Horace M. Kallen, an American philosopher known for his advocacy of cultural pluralism.
-
B.
Kassis
Kassis is a family name of likely Levantine, particularly Palestinian or broader Arab, origin.
-
C.
Helikon
Helikon is a mountain in Greek mythology, often associated with the Muses and poetic inspiration.
-
D.
Stonn
Stonn is a Vulcan male from the Star Trek universe, best known as T'Pring's chosen mate in the original series episode "Amok Time."
-
E.
Ledaal
Ledaal is a historic manor house in Stavanger, Norway, that has served as a royal residence and cultural landmark.
- 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: Sonar Kella Triple: [Feluda series, hasWork, Sonar Kella]
Generated description
Sonar Kella is a popular Bengali detective novel by Satyajit Ray featuring the sleuth Feluda, centered on a mystery involving a supposed past life and a legendary golden fortress in Rajasthan.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Sonar Kella Target entity description: Sonar Kella is a popular Bengali detective novel by Satyajit Ray featuring the sleuth Feluda, centered on a mystery involving a supposed past life and a legendary golden fortress in Rajasthan.
-
A.
Kallen
Kallen is a surname most notably associated with Horace M. Kallen, an American philosopher known for his advocacy of cultural pluralism.
-
B.
Kassis
Kassis is a family name of likely Levantine, particularly Palestinian or broader Arab, origin.
-
C.
Helikon
Helikon is a mountain in Greek mythology, often associated with the Muses and poetic inspiration.
-
D.
Stonn
Stonn is a Vulcan male from the Star Trek universe, best known as T'Pring's chosen mate in the original series episode "Amok Time."
-
E.
Ledaal
Ledaal is a historic manor house in Stavanger, Norway, that has served as a royal residence and cultural landmark.
- 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_69c6888350588190870cd552b427a1cd |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6e6493fd88190b0c066a2ad74917c |
completed | March 27, 2026, 8:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7a32e8098819090b88fc920416f6b |
completed | March 28, 2026, 9:45 a.m. |
| NEDg | Description generation | batch_69c7a3f2b51c81909f058149e9bd9f0a |
completed | March 28, 2026, 9:48 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c7a4a9e91881909df07f1c540f191e |
completed | March 28, 2026, 9:51 a.m. |
Created at: March 27, 2026, 2:44 p.m.