Triple
T3179336
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Parish of Portland |
E66540
|
entity |
| Predicate | riverActivity |
P1477
|
FINISHED |
| Object | rafting on the Rio Grande |
—
|
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: rafting on the Rio Grande | Statement: [Parish of Portland, riverActivity, rafting on the Rio Grande]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: riverActivity Context triple: [Parish of Portland, riverActivity, rafting on the Rio Grande]
-
A.
hasRiverActivity
chosen
Indicates that an entity engages in, supports, or is associated with activities occurring on or along a river.
-
B.
riverManaged
Indicates that a river is subject to management, regulation, or oversight by a particular authority, organization, or system.
-
C.
waterwayStatus
Indicates the current navigational or operational condition of a waterway, such as whether it is open, restricted, or closed for use.
-
D.
streams
Indicates that one entity continuously transmits or delivers data, media, or content in real time to another entity.
-
E.
flowsAt
Indicates that a fluid or substance moves through or along a specific location, point, or 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_69ad8586a34c8190944c63ec11a8de1a |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada69f2d108190847922795e7b6687 |
completed | March 8, 2026, 4:41 p.m. |
| PD | Predicate disambiguation | batch_69ad9e02677c8190a21d93b1259b2761 |
completed | March 8, 2026, 4:04 p.m. |
Created at: March 8, 2026, 3:06 p.m.