Triple
T7212019
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Robert Macomb |
E149426
|
entity |
| Predicate | notableFor |
P22
|
FINISHED |
| Object | Macombs Dam |
E149944
|
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: Macombs Dam | Statement: [Robert Macomb, notableFor, Macombs Dam]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Macombs Dam Context triple: [Robert Macomb, notableFor, Macombs Dam]
-
A.
Macomb’s Dam
chosen
Macomb’s Dam was a historic Harlem River crossing in New York City that preceded and was ultimately superseded by the Macombs Dam Bridge.
-
B.
Shellmouth Dam
Shellmouth Dam is a major flood control and water management structure on the Assiniboine River in Manitoba, Canada, helping regulate river flow and protect downstream communities.
-
C.
Gillespie Dam
Gillespie Dam is an early 20th-century concrete gravity dam on Arizona’s Gila River, historically used for irrigation and now noted as a local landmark and wildlife habitat area.
-
D.
Wyman Dam
Wyman Dam is a hydroelectric dam in Maine that impounds the Kennebec River to form Wyman Lake and generate power.
-
E.
Wyman Dam
Wyman Dam is a hydroelectric dam located on the Androscoggin River in Maine, used for power generation and river flow regulation.
- 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_69c687eca814819095abb52316b1af80 |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6e96f99088190a085476bcfca26fd |
completed | March 27, 2026, 8:32 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c8682696a48190aec021bd00c6f633 |
completed | March 28, 2026, 11:45 p.m. |
Created at: March 27, 2026, 2:53 p.m.