Triple
T456671
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Georgian script |
E7247
|
entity |
| Predicate | writingMediumHistorical |
P13697
|
FINISHED |
| Object | stone inscriptions |
—
|
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: stone inscriptions | Statement: [Georgian script, writingMediumHistorical, stone inscriptions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: writingMediumHistorical Context triple: [Georgian script, writingMediumHistorical, stone inscriptions]
-
A.
historicalScript
Indicates that an entity is or was written in, or otherwise associated with, a particular historical writing system or script.
-
B.
historicalForm
Indicates that one entity is an earlier or historically attested form or variant of another entity.
-
C.
historicalReference
Indicates that one entity refers to, cites, or alludes to another entity from an earlier time or historical context.
-
D.
historicalCategory
Indicates that an entity is classified within a particular historical grouping, period, or type based on its time-related characteristics or context.
-
E.
historicallyIn
Indicates that one entity existed, occurred, or was situated within the historical context, period, or jurisdiction associated with another 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_69a2e7e5c5bc8190a1dc8178218fba40 |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2efa1616481909399f92551a0c9e3 |
completed | Feb. 28, 2026, 1:37 p.m. |
| PD | Predicate disambiguation | batch_69a2ede614b88190be07425f5535f56d |
completed | Feb. 28, 2026, 1:30 p.m. |
| PDg | Predicate description generation | batch_69a2ee8b56d08190bd625626353d01b4 |
completed | Feb. 28, 2026, 1:32 p.m. |
Created at: Feb. 28, 2026, 1:12 p.m.