Triple
T25655618
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ananda Publishers |
E643224
|
entity |
| Predicate | scriptOfPublication |
P74999
|
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: [Ananda Publishers, scriptOfPublication, Bengali script]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: scriptOfPublication Context triple: [Ananda Publishers, scriptOfPublication, Bengali script]
-
A.
scriptOfReferent
chosen
Indicates that a script (e.g., writing system or code) is associated with, or used to represent, a particular referent.
-
B.
publicationBody
Indicates the organization or entity that serves as the publishing body responsible for issuing the referenced work.
-
C.
scriptOfOrigin
Indicates that one entity is the original writing system or script from which another script is derived or historically originates.
-
D.
publicationDetail
Indicates the specific publication-related information associated with an entity, such as how, where, or in what form it is published.
-
E.
publicationAbout
Indicates that a publication has content whose subject or focus is the referenced 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_69e77e7d8a848190a98d0162325fd780 |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f5faeafa50819082a180ac76b05b57 |
completed | May 2, 2026, 1:23 p.m. |
| PD | Predicate disambiguation | batch_69f5afec3e94819080d9ba86cf8c866e |
completed | May 2, 2026, 8:03 a.m. |
Created at: April 21, 2026, 6:32 p.m.