Triple
T29572272
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roman engineering |
E753343
|
entity |
| Predicate | usedInfrastructureElement |
P9772
|
FINISHED |
| Object | milestone |
—
|
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: milestone | Statement: [Roman engineering, usedInfrastructureElement, milestone]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedInfrastructureElement Context triple: [Roman engineering, usedInfrastructureElement, milestone]
-
A.
usesInfrastructure
Indicates that one entity makes use of, depends on, or operates through the infrastructure provided or managed by another entity.
-
B.
usesInfrastructurePreviouslyOwnedBy
Indicates that one entity makes use of infrastructure that was formerly owned by another entity.
-
C.
infrastructureReuse
Indicates that existing infrastructure is being used again for a new or continued purpose instead of building or deploying entirely new infrastructure.
-
D.
containedInfrastructure
Indicates that one infrastructure element is physically or logically contained within another infrastructure element.
-
E.
usedComponent
chosen
Indicates that one entity has employed or incorporated another entity as a component in its structure, function, or operation.
- 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_69f0ef7fcb4881908a933110adb9bda1 |
completed | April 28, 2026, 5:33 p.m. |
| NER | Named-entity recognition | batch_69fcec5f8b448190b48330a19b462d24 |
completed | May 7, 2026, 7:47 p.m. |
| PD | Predicate disambiguation | batch_69fceaf1e23881908ca24160a638e329 |
completed | May 7, 2026, 7:41 p.m. |
Created at: April 28, 2026, 5:59 p.m.