Triple
T16314955
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dùn Èideann |
E396149
|
entity |
| Predicate | hasRiver |
P165
|
FINISHED |
| Object | Water of Leith |
E671301
|
NE 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: Water of Leith | Statement: [Dùn Èideann, hasRiver, Water of Leith]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Water of Leith Context triple: [Dùn Èideann, hasRiver, Water of Leith]
-
A.
Water of Leith
chosen
The Water of Leith is the main river flowing through Edinburgh, Scotland, running from the Pentland Hills to the Firth of Forth and historically powering much of the city’s industry.
-
B.
Murieston Water
Murieston Water is a small river in West Lothian, Scotland, that flows through the Murieston area before joining the River Almond.
-
C.
Jordan Creek
Jordan Creek is a tributary stream in eastern Pennsylvania that flows through Lehigh County before joining the Lehigh River.
-
D.
Jordan Creek
Jordan Creek is a stream in the northwestern United States that flows through parts of Idaho and Oregon before joining the Owyhee River.
-
E.
Shotts Burn
Shotts Burn is a small stream in North Lanarkshire, Scotland, that flows through the town of Shotts before joining the South Calder Water.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d87f255b788190a400eba031dd85d8 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e288de57cc81908cec93309347c385 |
completed | April 17, 2026, 7:24 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a001fa88e8c8190b0423b60389896dc |
completed | May 10, 2026, 6:03 a.m. |
Created at: April 10, 2026, 5:06 a.m.