Triple
T18411396
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Etruscan mirrors |
E441765
|
entity |
| Predicate | reflectiveSide |
P3935
|
FINISHED |
| Object | polished bronze surface |
—
|
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: polished bronze surface | Statement: [Etruscan mirrors, reflectiveSide, polished bronze surface]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reflectiveSide Context triple: [Etruscan mirrors, reflectiveSide, polished bronze surface]
-
A.
reflects
chosen
Indicates that one entity (often a surface, medium, or representation) throws back, mirrors, or otherwise shows an image, property, or state of another entity.
-
B.
onSide
Indicates that one entity is positioned along or adjacent to the side of another entity.
-
C.
secondaryMirrorShape
Indicates that one entity specifies or defines the geometric shape of a secondary mirror associated with another entity.
-
D.
obverseOrReverse
Indicates that two sides or aspects of the same object or item are being related as its obverse (front) and reverse (back).
-
E.
mirroredAt
Indicates that one entity is a mirror image or reflection of another entity with respect to a specified axis, plane, or point.
- 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_69d8b9eb8a508190a942fd75ebd8b1dc |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e51a24e130819082b92f98d8d5fa3c |
completed | April 19, 2026, 6:08 p.m. |
| PD | Predicate disambiguation | batch_69e469bf7f74819096a01173493412c2 |
completed | April 19, 2026, 5:35 a.m. |
Created at: April 10, 2026, 10:47 a.m.