Triple
T19320079
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Randalstown |
E483198
|
entity |
| Predicate | hasRiver |
P165
|
FINISHED |
| Object | River Main |
—
|
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 Main | Statement: [Randalstown, hasRiver, River Main]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: River Main Context triple: [Randalstown, hasRiver, River Main]
-
A.
River Main
The River Main is a major waterway in central Germany that flows through cities such as Frankfurt before joining the Rhine.
-
B.
River Main
chosen
River Main is a river in Northern Ireland that flows through County Antrim and joins the River Braid before eventually reaching the sea via Lough Neagh and the Lower Bann.
-
C.
Spring River
Spring River is a tributary of the Arkansas River that flows through parts of Kansas, Missouri, and Oklahoma in the central United States.
-
D.
You River
The You River is a tributary waterway in southern China that feeds into the larger Yuan River system.
-
E.
Train River
The Train River is a smaller watercourse in Belgium that serves as a tributary within the Dyle River basin.
- 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_69d8e8d13e3c81909d91d1d5ec37c095 |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e60d87a0088190a60201b1f388089e |
completed | April 20, 2026, 11:27 a.m. |
Created at: April 10, 2026, 1:32 p.m.