Triple
T23667779
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shaheed Salam Barkat Hall |
E584632
|
entity |
| Predicate | hasLanguageOfInstructionAtInstitution |
P36232
|
FINISHED |
| Object | Bengali |
—
|
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 | Statement: [Shaheed Salam Barkat Hall, hasLanguageOfInstructionAtInstitution, Bengali]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLanguageOfInstructionAtInstitution Context triple: [Shaheed Salam Barkat Hall, hasLanguageOfInstructionAtInstitution, Bengali]
-
A.
alsoUsesLanguageOfInstruction
Indicates that an entity, in addition to its primary language, uses the same language that is designated as the language of instruction in a given context.
-
B.
hasLanguageOfStudy
Indicates that an entity studies or is engaged in learning a particular language.
-
C.
languageOfAwardingInstitution
Indicates the language in which the awarding institution formally grants or documents the award.
-
D.
languageOfTeachings
chosen
Indicates the language in which teachings, lessons, or instructional content are delivered or expressed.
-
E.
languageBranchStudied
Indicates that a person studies or has studied a particular branch or subgroup of a language.
- 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_69e24901421881908c17a5293bdd4a8e |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b40d0e208190969fecbede5979b8 |
completed | April 29, 2026, 7:32 a.m. |
| PD | Predicate disambiguation | batch_69f118dd13008190a8799b4e9cadbd79 |
completed | April 28, 2026, 8:30 p.m. |
Created at: April 17, 2026, 6:50 p.m.