Triple
T27416312
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hindu epics |
E692903
|
entity |
| Predicate | traditionallyWrittenIn |
P23831
|
FINISHED |
| Object | Sanskrit |
—
|
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: Sanskrit | Statement: [Hindu epics, traditionallyWrittenIn, Sanskrit]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: traditionallyWrittenIn Context triple: [Hindu epics, traditionallyWrittenIn, Sanskrit]
-
A.
isWrittenWith
Indicates that something is created or expressed using a particular writing tool, medium, or system.
-
B.
currentlyWrittenIn
chosen
Indicates that a work or document is, at the present time, expressed or composed in a particular language or writing system.
-
C.
hasWritingTraditionVia
Indicates that an entity possesses or participates in a writing tradition by means of, or through the mediation of, another specified entity or method.
-
D.
canBeWrittenIn
Indicates that something is capable of being expressed, encoded, or represented using a particular language, notation, or medium.
-
E.
writingSystemUsedIn
Indicates that a particular writing system is employed for written communication within a given language, region, or context.
- 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_69ef5208617081908f731d312e0fd1bc |
completed | April 27, 2026, 12:09 p.m. |
| NER | Named-entity recognition | batch_69fb2e940d5c8190bceae77daf4ef512 |
completed | May 6, 2026, 12:05 p.m. |
| PD | Predicate disambiguation | batch_69f9fec70bd881909c658a3c5020318b |
completed | May 5, 2026, 2:29 p.m. |
Created at: April 27, 2026, 12:34 p.m.