Triple
T27352717
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | R. H. Saunders Generating Station |
E684405
|
entity |
| Predicate | sharesDamComplexWith |
P37166
|
FINISHED |
| Object | Robert Moses Niagara Power Plant |
—
|
NE NERFINISHED |
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: Robert Moses Niagara Power Plant | Statement: [R. H. Saunders Generating Station, sharesDamComplexWith, Robert Moses Niagara Power Plant]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sharesDamComplexWith Context triple: [R. H. Saunders Generating Station, sharesDamComplexWith, Robert Moses Niagara Power Plant]
-
A.
sharesDamWith
Indicates that two entities are impounded or regulated by the same dam structure.
-
B.
sharesComplexWith
chosen
Indicates that two entities are components of, or co-residents within, the same larger complex or composite structure.
-
C.
sharesFacilityWith
Indicates that two entities use or have access to the same physical facility or location.
-
D.
sharesCorridorWith
Indicates that two entities are located along or connected by the same corridor or passageway.
-
E.
sharesBuildingWith
Indicates that two entities occupy or use the same building.
- 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_69ef1480a76481908684256ddd5bfda3 |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69fcf825ca7081909d06b0df33eb33f9 |
completed | May 7, 2026, 8:37 p.m. |
| PD | Predicate disambiguation | batch_69fcf42160f0819096812a8bf590875e |
completed | May 7, 2026, 8:20 p.m. |
Created at: April 27, 2026, 11:49 a.m.