Triple
T25683963
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Goddess Kamakhya |
E644016
|
entity |
| Predicate | languageOfMajorDevotion |
P136332
|
FINISHED |
| Object | Assamese |
—
|
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: Assamese | Statement: [Goddess Kamakhya, languageOfMajorDevotion, Assamese]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: languageOfMajorDevotion Context triple: [Goddess Kamakhya, languageOfMajorDevotion, Assamese]
-
A.
dominantReligion
Indicates the religion that holds primary or majority status within a given group, region, or entity.
-
B.
languageOfReligion
Indicates the language in which a particular religion is traditionally expressed, practiced, or documented.
-
C.
languageOfDevotees
chosen
Indicates the language commonly used or spoken by a group of devotees in their religious or devotional practices.
-
D.
laterReligionDominant
Indicates that a religion adopted or followed at a later time becomes the dominant or primary religion in the relevant context or entity.
-
E.
languageOfWorship
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_69e77e8046888190b07ffa58c7e2c37a |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f73223675481908c1bc3208c0f5284 |
completed | May 3, 2026, 11:31 a.m. |
| PD | Predicate disambiguation | batch_69f7317690108190b3aae2cd2e1d069e |
completed | May 3, 2026, 11:28 a.m. |
Created at: April 21, 2026, 8:05 p.m.