Triple
T19548141
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Varadaraja Perumal |
E489127
|
entity |
| Predicate | languageOfPrimaryLiturgicalTexts |
P3115
|
FINISHED |
| Object | Tamil |
—
|
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: Tamil | Statement: [Varadaraja Perumal, languageOfPrimaryLiturgicalTexts, Tamil]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: languageOfPrimaryLiturgicalTexts Context triple: [Varadaraja Perumal, languageOfPrimaryLiturgicalTexts, Tamil]
-
A.
usesPrimaryLiturgicalLanguageHistorically
Indicates that an entity has historically used a particular primary liturgical language in its religious rites or worship practices.
-
B.
liturgicalLanguageVersion
Indicates that one entity is a specific version or form of another entity expressed in a particular liturgical language.
-
C.
languageOfCreeds
Indicates the language in which formal creeds, confessions, or doctrinal statements are expressed or officially formulated.
-
D.
typicalLanguageOfReadings
Indicates the language that is most commonly used for readings or interpretations associated with a given entity.
-
E.
languageOfWorship
chosen
Indicates the language in which religious worship, rituals, or liturgical practices are conducted.
- 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_69d8e8db5b6c8190984b61f91981f575 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e63d2e5e588190ac3a6f612d4fb54b |
completed | April 20, 2026, 2:50 p.m. |
| PD | Predicate disambiguation | batch_69e514d4df3c8190b7e9b3b4fdf9452a |
completed | April 19, 2026, 5:45 p.m. |
Created at: April 10, 2026, 1:41 p.m.