Triple
T23878703
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Atlantic Coast watershed |
E600138
|
entity |
| Predicate | includesWatercourseType |
P27890
|
FINISHED |
| Object | river |
—
|
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: river | Statement: [Atlantic Coast watershed, includesWatercourseType, river]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: includesWatercourseType Context triple: [Atlantic Coast watershed, includesWatercourseType, river]
-
A.
hasWatercourseType
chosen
Indicates the specific kind or category of watercourse (such as river, stream, or canal) associated with an entity.
-
B.
isNaturalWatercourse
Indicates that one entity is a naturally formed flowing body of water (such as a river or stream), rather than an artificial or man-made channel.
-
C.
isOnWatercourse
Indicates that one entity is situated directly on, above, or along the path of a watercourse such as a river, stream, or canal.
-
D.
inflowWatercourse
Indicates that one watercourse flows into or feeds another water body or watercourse.
-
E.
watercourseSupports
Indicates that a watercourse provides the necessary conditions or resources to sustain another entity, process, or activity.
- 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_69e295318e148190b9979d8fc02e168f |
completed | April 17, 2026, 8:16 p.m. |
| NER | Named-entity recognition | batch_69f1cc032c9c81909986ae6f672c1ad1 |
completed | April 29, 2026, 9:14 a.m. |
| PD | Predicate disambiguation | batch_69f1614a65a88190bde1efb368a151e4 |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 8:23 p.m.