Triple
T25674979
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tarapith Tara Temple |
E643779
|
entity |
| Predicate | languageOfLocalPractice |
P65907
|
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: [Tarapith Tara Temple, languageOfLocalPractice, Bengali]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: languageOfLocalPractice Context triple: [Tarapith Tara Temple, languageOfLocalPractice, Bengali]
-
A.
hasLanguageOfPractice
chosen
Indicates that an entity uses or operates in a particular language as its regular or primary medium of practice.
-
B.
languageOfCommunications
Indicates that a specified language is used as the medium for communications associated with an entity or interaction.
-
C.
languageOfProvision
Indicates the language in which a provision, such as a legal or contractual clause, is written or officially expressed.
-
D.
languageUsedInLocality
Indicates that a particular language is used or spoken within a specific locality or geographic area.
-
E.
languageOfJurisdiction
Indicates the language officially used for legal and administrative purposes within a given jurisdiction.
- 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_69e77e7f69808190ad27df1006f6037a |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f72921cf2c8190909bb53f78bcc890 |
completed | May 3, 2026, 10:53 a.m. |
| PD | Predicate disambiguation | batch_69f7283d8cec8190b524c144948bc4ec |
completed | May 3, 2026, 10:49 a.m. |
Created at: April 21, 2026, 7:36 p.m.