Triple
T26125869
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Upanyas Samagra |
E659101
|
entity |
| Predicate | isCollectedWorkOf |
P108224
|
FINISHED |
| Object | novels by Al Mahmud |
—
|
LITERAL 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: novels by Al Mahmud | Statement: [Upanyas Samagra, isCollectedWorkOf, novels by Al Mahmud]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isCollectedWorkOf Context triple: [Upanyas Samagra, isCollectedWorkOf, novels by Al Mahmud]
-
A.
isAWorkBy
Indicates that one entity is a creative work that has been produced or authored by another entity.
-
B.
containsWorksFrom
Indicates that one entity includes or holds works that originate from or are created by another entity.
-
C.
isPosthumousWorkOf
Indicates that a work was created, published, or became known only after the death of the person with whom it is associated.
-
D.
appearsInWorkByAuthorFrom
Indicates that an entity appears in a work that was created by an author originating from a specified place or country.
-
E.
worksCollectedAs
chosen
Indicates that multiple individual works are gathered, compiled, or published together as a single collected entity.
- F. None of above.
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_69ee5bc2b2948190b458ad3f580af779 |
completed | April 26, 2026, 6:38 p.m. |
| NER | Named-entity recognition | batch_69f60b8eeeb48190a192fa8ba8cc20bf |
completed | May 2, 2026, 2:34 p.m. |
| PD | Predicate disambiguation | batch_69f5b0021da88190bdd4cf2698c23edf |
completed | May 2, 2026, 8:04 a.m. |
Created at: April 26, 2026, 8:11 p.m.