Triple
T35661631
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roman gold mining system of northwestern Iberian Peninsula |
E1030449
|
entity |
| Predicate | miningTechnique |
P10923
|
FINISHED |
| Object | ruina montium |
—
|
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: ruina montium | Statement: [Roman gold mining system of northwestern Iberian Peninsula, miningTechnique, ruina montium]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: miningTechnique Context triple: [Roman gold mining system of northwestern Iberian Peninsula, miningTechnique, ruina montium]
-
A.
miningMethod
chosen
Indicates the technique or process used to extract minerals or resources from the earth.
-
B.
mainMiningMethod
Indicates the primary mining technique or process predominantly used in extracting resources at a given site or operation.
-
C.
miningScale
Indicates the relative size or intensity of a mining operation or activity.
-
D.
miningRole
Indicates a role or function specifically associated with performing or supporting mining activities.
-
E.
miningSite
Indicates a location where mining activities or mineral extraction operations take place.
- 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_69f76e09f87881909c954aaac176c34f |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f79fa7d1708190bb5defe2ea54dc75 |
completed | May 3, 2026, 7:19 p.m. |
| PD | Predicate disambiguation | batch_69f79e4d885881908a3612e2e75cf84f |
completed | May 3, 2026, 7:13 p.m. |
Created at: May 3, 2026, 4:05 p.m.