Triple
T18683918
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dead Vistula |
E456805
|
entity |
| Predicate | hasEngineeringWorks |
P67599
|
FINISHED |
| Object | embankments |
—
|
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: embankments | Statement: [Dead Vistula, hasEngineeringWorks, embankments]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasEngineeringWorks Context triple: [Dead Vistula, hasEngineeringWorks, embankments]
-
A.
hasEngineeringBy
Indicates that something is designed, planned, or constructed by a specified engineer or engineering entity.
-
B.
hasEngineeringFunction
Indicates that an entity possesses or performs a specific engineering-related role, purpose, or operational function.
-
C.
hasMaintenanceProjectsBy
Indicates that one entity is responsible for or associated with carrying out maintenance projects on another entity.
-
D.
hasWorkProduct
chosen
Indicates that one entity produces, creates, or is responsible for a particular work product or output associated with it.
-
E.
hasWorkOn
Indicates that one entity is associated with, contributes to, or performs work on another entity (such as a project, task, or artifact).
- 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_69d8d391eb488190ac2e9abf5bf255e4 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e55b2b819c8190b5f3d7a88607f6f5 |
completed | April 19, 2026, 10:46 p.m. |
| PD | Predicate disambiguation | batch_69e478db7a248190a8c6584673773923 |
completed | April 19, 2026, 6:40 a.m. |
Created at: April 10, 2026, 11:49 a.m.