Triple
T20850329
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Strathmore |
E513339
|
entity |
| Predicate | watercourse |
P415
|
FINISHED |
| Object | River Isla |
—
|
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: River Isla | Statement: [Strathmore, watercourse, River Isla]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: River Isla Context triple: [Strathmore, watercourse, River Isla]
-
A.
River Isla
River Isla is a river in northeastern Scotland that flows through rural landscapes and farmland before joining the River Deveron.
-
B.
River Isla
chosen
River Isla is a river in eastern Scotland that flows through Perth and Kinross before joining the River Tay.
-
C.
Lagoona
Lagoona is a creative work or character whose style and themes are shaped by the fantastical, fairy-filled world and motifs associated with Oberon from literature and mythology.
-
D.
Tamanique
Tamanique is a small town and municipality in western El Salvador known for its nearby waterfalls and coastal proximity.
-
E.
Isla
Isla is a Spanish surname historically associated with figures such as 18th-century naval officer Luis Vicente de Velasco e Isla.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b4f4898081908209e58edb8f9c45 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c352ca8c819094545dbe67bfe3dc |
completed | April 21, 2026, 12:22 a.m. |
Created at: April 16, 2026, 12:43 p.m.