Triple
T6240010
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Durgeshnandini |
E139574
|
entity |
| Predicate | scriptOfOriginalEdition |
P69719
|
FINISHED |
| Object | Bengali script |
—
|
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: Bengali script | Statement: [Durgeshnandini, scriptOfOriginalEdition, Bengali script]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: scriptOfOriginalEdition Context triple: [Durgeshnandini, scriptOfOriginalEdition, Bengali script]
-
A.
scriptOfOrigin
Indicates that one entity is the original writing system or script from which another script is derived or historically originates.
-
B.
originalRelease
Indicates the initial publication or first official release event of a work or product.
-
C.
scriptOfTitle
Indicates that a script (e.g., a written work or screenplay) is associated with or belongs to a particular titled work.
-
D.
originallyWrittenFor
Indicates that a work was initially created or composed with a particular recipient, medium, context, or purpose in mind.
-
E.
originallyTitleOf
Indicates that one title is the original title from which another work, edition, or localized title is derived.
- F. None of above. chosen
Provenance (4 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_69c008b0e7ac8190808a59573ee646f3 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c063067d9c819085a18d9d03939266 |
completed | March 22, 2026, 9:45 p.m. |
| PD | Predicate disambiguation | batch_69c05601de6481909d0880048fd7b49a |
completed | March 22, 2026, 8:50 p.m. |
| PDg | Predicate description generation | batch_69c05707d5408190a1d0fd80414ad957 |
completed | March 22, 2026, 8:54 p.m. |
Created at: March 22, 2026, 4:23 p.m.