Triple
T2211431
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hudson River tunnels |
E50924
|
entity |
| Predicate | engineeringType |
P7599
|
FINISHED |
| Object | subaqueous tunnel |
—
|
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: subaqueous tunnel | Statement: [Hudson River tunnels, engineeringType, subaqueous tunnel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: engineeringType Context triple: [Hudson River tunnels, engineeringType, subaqueous tunnel]
-
A.
engineeringFeature
Indicates that one entity serves as an engineering-related feature, component, or characteristic of another entity within a technical or designed system.
-
B.
constructionType
chosen
Indicates the specific method or style by which something is built or constructed.
-
C.
hasStructuralEngineer
Indicates that an entity is associated with or employs a structural engineer responsible for its structural design, analysis, or integrity.
-
D.
laterEngineer
Indicates that one entity becomes an engineer at a later time than another entity.
-
E.
architectureType
Indicates the specific style or category of architecture that characterizes or defines an 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_69a88b06709c8190978fb2418470d1b6 |
completed | March 4, 2026, 7:41 p.m. |
| NER | Named-entity recognition | batch_69abbfeb889081908cddf58a57b216df |
completed | March 7, 2026, 6:04 a.m. |
| PD | Predicate disambiguation | batch_69abbdaa26d48190860c33fd464c4845 |
completed | March 7, 2026, 5:54 a.m. |
Created at: March 4, 2026, 7:46 p.m.