Triple
T38078859
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Atlantic Ocean via Merrimack River |
E950795
|
entity |
| Predicate | flowsIntoNearCity |
P47623
|
FINISHED |
| Object | Newburyport, Massachusetts |
—
|
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: Newburyport, Massachusetts | Statement: [Atlantic Ocean via Merrimack River, flowsIntoNearCity, Newburyport, Massachusetts]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: flowsIntoNearCity Context triple: [Atlantic Ocean via Merrimack River, flowsIntoNearCity, Newburyport, Massachusetts]
-
A.
flowsThroughTown
Indicates that something, typically a river or stream, passes through the area or boundaries of a town.
-
B.
flowsIntoBodyOfWaterNearCity
chosen
Indicates that a body of water flows into another body of water located in the vicinity of a specified city.
-
C.
passesNearCity
Indicates that the path, route, or trajectory of one entity goes close to, but not necessarily through, a specified city.
-
D.
flowsNearAdministrativeRegion
Indicates that a flowing feature (such as a river or stream) passes in close proximity to a specified administrative region without necessarily passing through it.
-
E.
flowsTowardRegion
Indicates that something (such as a fluid, substance, or traffic) moves in the direction of and approaches a specified region.
- 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_69f76f02a6c48190a94f3c0b3ee90cf2 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fc4748843c8190931432653be4890c |
completed | May 7, 2026, 8:03 a.m. |
| PD | Predicate disambiguation | batch_69fc45646ce481908caf292ff9f06e15 |
completed | May 7, 2026, 7:55 a.m. |
Created at: May 3, 2026, 4:21 p.m.