Triple
T11710295
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Uplistsikhe |
E278355
|
entity |
| Predicate | roofStructures |
P100895
|
FINISHED |
| Object | many caves partly reconstructed with modern brickwork |
—
|
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: many caves partly reconstructed with modern brickwork | Statement: [Uplistsikhe, roofStructures, many caves partly reconstructed with modern brickwork]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roofStructures Context triple: [Uplistsikhe, roofStructures, many caves partly reconstructed with modern brickwork]
-
A.
roofFeature
Indicates that one entity is a feature, element, or characteristic that is part of or associated with a roof.
-
B.
roofOptions
Indicates the available types or configurations of roofs that can be selected or applied to an entity.
-
C.
buildingStructure
Indicates that one entity is a structural component or physical part that forms, supports, or constitutes the construction of another entity.
-
D.
roofSpan
Indicates the horizontal distance or extent that a roof covers between its supporting points or walls.
-
E.
hasTypeOfRoof
Indicates that an entity possesses or is characterized by a specific kind or style of roof.
- 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_69d6aaff2ce88190b4a1e4b341ad5377 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a49f072c81909c6a964a92e5bc0c |
completed | April 10, 2026, 7:19 a.m. |
| PD | Predicate disambiguation | batch_69d88a7d483081909c2a101087515d74 |
completed | April 10, 2026, 5:28 a.m. |
| PDg | Predicate description generation | batch_69d890458d948190b15054c9ba0fd923 |
completed | April 10, 2026, 5:53 a.m. |
Created at: April 8, 2026, 9:40 p.m.