Triple
T8146233
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Watertown Dam |
E190217
|
entity |
| Predicate | usedToPower |
P11313
|
FINISHED |
| Object | mills in Watertown |
—
|
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: mills in Watertown | Statement: [Watertown Dam, usedToPower, mills in Watertown]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedToPower Context triple: [Watertown Dam, usedToPower, mills in Watertown]
-
A.
usesElectricityFor
Indicates that one entity relies on or employs electricity as the power source to operate, perform a function, or carry out an activity for another entity or purpose.
-
B.
hasPowerSource
Indicates that an entity derives its operational energy or functionality from a specified power source.
-
C.
suppliesPowerTo
chosen
Indicates that one entity provides electrical or energy power required for the operation or functioning of another entity.
-
D.
intendedPower
Indicates the level or amount of power that an entity is designed, planned, or expected to produce, use, or deliver under intended operating conditions.
-
E.
electrificationUsedFor
Indicates that electrification is employed as a means or method to achieve, enable, or support a particular function, process, or purpose.
- 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_69ca82be7ba8819087de0147e9292c83 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb4447dbc48190affb0f34f6c85f5a |
completed | March 31, 2026, 3:49 a.m. |
| PD | Predicate disambiguation | batch_69cb369c0d0481908762c488d7f77e74 |
completed | March 31, 2026, 2:51 a.m. |
Created at: March 30, 2026, 5:36 p.m.