Triple
T6096394
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Grantha (Unicode block) |
E135887
|
entity |
| Predicate | scriptUsagePeriod |
P68103
|
FINISHED |
| Object | medieval South India |
—
|
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: medieval South India | Statement: [Grantha (Unicode block), scriptUsagePeriod, medieval South India]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: scriptUsagePeriod Context triple: [Grantha (Unicode block), scriptUsagePeriod, medieval South India]
-
A.
scriptUsedCurrently
Indicates that a particular writing system or script is the one presently in use for a given language, text, or context.
-
B.
sawServicePeriod
Indicates that one entity observed or was aware of the duration or specific period during which a service was provided or active.
-
C.
usedSince
Indicates that an entity has been in use starting from a specified point in time and continuing thereafter.
-
D.
inUseSince
Indicates that an entity has been actively in use starting from a specified point in time.
-
E.
durationOfUse
Indicates the length of time for which something is used or remains in use.
- 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_69c0087cd3c48190b459848c72d84eb1 |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c05a9764048190ad4e9a02f9a25ab6 |
completed | March 22, 2026, 9:09 p.m. |
| PD | Predicate disambiguation | batch_69c049f5ac988190b62ba565153aaa35 |
completed | March 22, 2026, 7:58 p.m. |
| PDg | Predicate description generation | batch_69c04e8e3f2c8190be459ca02f9b315a |
completed | March 22, 2026, 8:18 p.m. |
Created at: March 22, 2026, 4:12 p.m.