Triple
T19778806
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tammerkoski rapids |
E475077
|
entity |
| Predicate | hasNearbyDistrict |
P4647
|
FINISHED |
| Object | Finlayson |
—
|
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: Finlayson | Statement: [Tammerkoski rapids, hasNearbyDistrict, Finlayson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Finlayson Context triple: [Tammerkoski rapids, hasNearbyDistrict, Finlayson]
-
A.
Finlayson
chosen
Finlayson is a Scottish surname historically associated with several notable figures in politics, industry, and the arts.
-
B.
Finnis
Finnis is a surname most notably associated with John Finnis, an influential legal philosopher known for his work on natural law theory.
-
C.
Fergus
Fergus is a fictional character from the game "Wild Target," likely serving as a notable figure within its story or gameplay.
-
D.
Fergus
Fergus is a historic small town in southwestern Ontario, Canada, known for its Scottish heritage and annual Scottish Festival and Highland Games.
-
E.
Fergus
Fergus is one of Princess Fiona and Shrek’s ogre triplet sons in the Shrek animated film series.
- 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_69d8e51a43a08190956bc6df13c91a77 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6538230488190b45cd8aaec658f7f |
completed | April 20, 2026, 4:25 p.m. |
Created at: April 10, 2026, 1:49 p.m.