Triple
T20964614
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kathaka |
E516333
|
entity |
| Predicate | hasPreservationMedium |
P53051
|
FINISHED |
| Object | palm-leaf manuscripts (historically) |
—
|
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: palm-leaf manuscripts (historically) | Statement: [Kathaka, hasPreservationMedium, palm-leaf manuscripts (historically)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPreservationMedium Context triple: [Kathaka, hasPreservationMedium, palm-leaf manuscripts (historically)]
-
A.
hasSubjectOfPreservation
Indicates that something is the specific focus or object being preserved or conserved within a preservation relationship.
-
B.
hasPreservationConditions
Indicates the specific environmental or handling conditions required to properly preserve or maintain an entity.
-
C.
preservationType
Indicates the method or process by which something is preserved or kept from deterioration.
-
D.
hasPhysicalMedium
chosen
Indicates that one entity serves as the tangible carrier or material form through which another entity exists, is stored, or is transmitted.
-
E.
preservationFormat
Indicates the format or encoding in which something is maintained specifically for long-term preservation.
- 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_69e0b4fde6c48190af1398e7e734629e |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6fb71d644819087e00933fcc26217 |
completed | April 21, 2026, 4:22 a.m. |
| PD | Predicate disambiguation | batch_69e5dbe6976081908abd4e9c8734bae9 |
completed | April 20, 2026, 7:55 a.m. |
Created at: April 16, 2026, 1:32 p.m.