Triple
T17979494
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Adhyatma Ramayana |
E449561
|
entity |
| Predicate | hasNumberOfKandas |
P129983
|
FINISHED |
| Object | 7 |
—
|
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: 7 | Statement: [Adhyatma Ramayana, hasNumberOfKandas, 7]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNumberOfKandas Context triple: [Adhyatma Ramayana, hasNumberOfKandas, 7]
-
A.
hasNumberOfPrakaras
Indicates the relationship specifying how many prakaras (enclosure layers or surrounding structures) are associated with a given entity.
-
B.
kāṇḍa
Indicates a part–whole relationship where something is a section, chapter, or subdivision of a larger structured whole.
-
C.
hasNumberOfKoans
Indicates the relationship that specifies how many koans are associated with or contained by a given entity.
-
D.
hasNumberOfVarnas
Indicates the relationship that specifies how many varnas (distinct categories or classes) are associated with a given entity.
-
E.
hasNumberOfWuku
Indicates the relationship that specifies how many wuku (traditional Javanese calendar weeks) are associated with a given entity.
- F. None of above. chosen
Provenance (4 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_69d8b9f9927c8190a006110c8b996e61 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4b201d1508190a9d6abbfd04bdcae |
completed | April 19, 2026, 10:44 a.m. |
| PD | Predicate disambiguation | batch_69e3f8fa62688190a5d5c361ab896256 |
completed | April 18, 2026, 9:34 p.m. |
| PDg | Predicate description generation | batch_69e42d8d68288190a05dc5d7803cf823 |
completed | April 19, 2026, 1:19 a.m. |
Created at: April 10, 2026, 10:22 a.m.