Triple
T25285945
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lapidarium with Trajan’s Column replica |
E633939
|
entity |
| Predicate | replicaScale |
P18373
|
FINISHED |
| Object | full-scale |
—
|
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: full-scale | Statement: [Lapidarium with Trajan’s Column replica, replicaScale, full-scale]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: replicaScale Context triple: [Lapidarium with Trajan’s Column replica, replicaScale, full-scale]
-
A.
replicasDisplayedIn
Indicates that replica versions of an item are presented or shown within a particular location, context, or medium.
-
B.
replicaOf
chosen
Indicates that one entity is an exact or near-exact copy of another entity, preserving its form, structure, or content.
-
C.
replicaOperator
Indicates that an entity functions as an operator responsible for managing or controlling replicas of another entity.
-
D.
supportsDataReplicationFactor
Indicates that an entity enables, configures, or is compatible with a specified data replication factor for storing or duplicating data.
-
E.
replicaBuilt
Indicates that one entity has been constructed as a copy or reproduction of another entity.
- 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_69e75a9402fc81909362ca85277c06d9 |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f48e0921ac8190a4a8fec7be7ad8f6 |
completed | May 1, 2026, 11:27 a.m. |
| PD | Predicate disambiguation | batch_69f45d06d0388190b36ecde92013624a |
completed | May 1, 2026, 7:57 a.m. |
Created at: April 21, 2026, 1:19 p.m.