Triple
T36895711
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Narva Waterfall |
E911882
|
entity |
| Predicate | riverMouthCountryDownstream |
P87832
|
FINISHED |
| Object | Estonia |
—
|
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: Estonia | Statement: [Narva Waterfall, riverMouthCountryDownstream, Estonia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: riverMouthCountryDownstream Context triple: [Narva Waterfall, riverMouthCountryDownstream, Estonia]
-
A.
riverMouthCountry
chosen
Indicates the country in which a river’s mouth (where it flows into another body of water) is located.
-
B.
riverMouthAt
Indicates that the mouth or endpoint of a river is located at a specified place or geographic feature.
-
C.
riverMouthBasin
Indicates that a river’s mouth lies within or drains into a particular drainage basin.
-
D.
riverMouthRegion
Indicates the region or area where a river flows into a larger body of water, such as a sea, lake, or another river.
-
E.
riverMouthEmptiesInto
Indicates that the mouth of a river flows into and discharges its water into another body of water, such as a sea, ocean, lake, or another river.
- 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_69f76e841b54819097e7fa768bbc70b2 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fb6fdc7eb081908ab8475efb38c430 |
completed | May 6, 2026, 4:44 p.m. |
| PD | Predicate disambiguation | batch_69fb5a986e588190b7a10892bd2ff44c |
completed | May 6, 2026, 3:13 p.m. |
Created at: May 3, 2026, 4:13 p.m.