Triple
T7739904
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | River Yarrow |
E175479
|
entity |
| Predicate | flowsNear |
P350
|
FINISHED |
| Object | Selkirk |
E134871
|
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: Selkirk | Statement: [River Yarrow, flowsNear, Selkirk]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Selkirk Context triple: [River Yarrow, flowsNear, Selkirk]
-
A.
Selkirk
chosen
Selkirk is a historic town in the Scottish Borders known for its legal heritage, including past judicial functions and associations with Scotland’s justice system.
-
B.
Kincorth
Kincorth is a residential area in the south of Aberdeen, Scotland, known for its post-war housing and proximity to the River Dee.
-
C.
Yekonyah
Yekonyah is an alternative name for Jehoiachin, the exiled king of Judah mentioned in the Hebrew Bible.
-
D.
Lumsden
Lumsden is a small rural town in New Zealand’s Southland region, serving as a local service and transport hub for the surrounding farming communities.
-
E.
Hokitika
Hokitika is a small coastal town on New Zealand’s South Island, known for its wild West Coast beaches, pounamu (greenstone) carving, and historic gold-mining heritage.
- 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_69c6995f9c60819092e386192bd63c6f |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c7035cddb881908bdfc1bd7d6a64ad |
completed | March 27, 2026, 10:23 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c8be4178408190850c284aab895442 |
completed | March 29, 2026, 5:53 a.m. |
Created at: March 27, 2026, 4:07 p.m.