Triple
T9739084
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Delaware Aqueduct |
E236139
|
entity |
| Predicate | bypassTunnelLength |
P12895
|
FINISHED |
| Object | approximately 2.5 miles |
—
|
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: approximately 2.5 miles | Statement: [Delaware Aqueduct, bypassTunnelLength, approximately 2.5 miles]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bypassTunnelLength Context triple: [Delaware Aqueduct, bypassTunnelLength, approximately 2.5 miles]
-
A.
hasTunnelLengthApprox
chosen
Indicates that an entity has a tunnel whose length is approximately a specified value.
-
B.
usesTunnel
Indicates that one entity makes use of a tunnel as a passage or route to reach or connect to another entity.
-
C.
tunnelType
Indicates the specific kind or classification of a tunnel associated with an entity.
-
D.
maximumBodyLength
Indicates that there is an upper limit on the allowable length or size of a body (e.g., content, message, or object) in this relationship or action.
-
E.
bypassType
Indicates the specific kind or method of bypass used to circumvent or route around a normal process, path, or control.
- 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_69ca84d313e88190983ee6ffd0ef60d2 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cd9ef43fec8190987628f401a27436 |
completed | April 1, 2026, 10:40 p.m. |
| PD | Predicate disambiguation | batch_69cd03cc128c81908b84ef224f858b4e |
completed | April 1, 2026, 11:38 a.m. |
Created at: March 30, 2026, 8:22 p.m.