Triple
T409345
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | River Mersey |
E9452
|
entity |
| Predicate | estuaryLocation |
P4359
|
FINISHED |
| Object | between Liverpool and the Wirral Peninsula |
—
|
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: between Liverpool and the Wirral Peninsula | Statement: [River Mersey, estuaryLocation, between Liverpool and the Wirral Peninsula]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: estuaryLocation Context triple: [River Mersey, estuaryLocation, between Liverpool and the Wirral Peninsula]
-
A.
hydrologicallyLocatedIn
Indicates that a water-related feature (such as a river, lake, or watershed) is situated within or associated with a specific geographic or administrative area in terms of hydrology.
-
B.
locatedOnWaterbody
Indicates that an entity is situated on or directly adjacent to a specified body of water.
-
C.
mouthOfTheWatercourse
chosen
Indicates the location where a watercourse ends and flows into a larger body of water.
-
D.
cityAtMouth
Indicates that a city is located at or very near the mouth (outlet) of a river.
-
E.
waterwayServed
Indicates that a place, facility, or infrastructure is served by, connected to, or functionally supported by a particular waterway.
- 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_69a2e80111fc8190961d5b7c6154123f |
completed | Feb. 28, 2026, 1:05 p.m. |
| NER | Named-entity recognition | batch_69a2ed31681c8190ac32334562fb17fd |
completed | Feb. 28, 2026, 1:27 p.m. |
| PD | Predicate disambiguation | batch_69a2e9737694819080fde9adcc1aa4d4 |
completed | Feb. 28, 2026, 1:11 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.