Triple
T12836057
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Delaware Lake |
E306915
|
entity |
| Predicate | formedBy |
P972
|
FINISHED |
| Object | Delaware Dam |
E470538
|
NE 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: Delaware Dam | Statement: [Delaware Lake, formedBy, Delaware Dam]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Delaware Dam Context triple: [Delaware Lake, formedBy, Delaware Dam]
-
A.
Delaware Dam
chosen
Delaware Dam is a flood-control and water-management structure located on the Olentangy River in central Ohio.
-
B.
West Point Dam
West Point Dam is a large U.S. Army Corps of Engineers hydroelectric and flood-control dam on the Chattahoochee River, forming West Point Lake on the Alabama–Georgia border.
-
C.
Jamestown Dam
Jamestown Dam is an earthfill dam in North Dakota that creates Jamestown Reservoir for flood control, irrigation, and recreation on the James River.
-
D.
Conklingville Dam
Conklingville Dam is a concrete gravity dam in New York that created the Great Sacandaga Lake reservoir for flood control and hydroelectric power generation.
-
E.
Irving Dam
Irving Dam is a man-made structure on Michigan’s Thornapple River used primarily for water level control and related river management.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d7bdf52b94819096d6f0ba4ab50a98 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96ff015f4819090070a01f3938acc |
completed | April 10, 2026, 9:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd646ee860819083277b15aaf510fd |
completed | May 8, 2026, 4:19 a.m. |
Created at: April 9, 2026, 5:35 p.m.