Triple
T4718012
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Isle of Mull |
E104695
|
entity |
| Predicate | hasNearbyIsland |
P970
|
FINISHED |
| Object | Ulva |
E118721
|
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: Ulva | Statement: [Isle of Mull, hasNearbyIsland, Ulva]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ulva Context triple: [Isle of Mull, hasNearbyIsland, Ulva]
-
A.
Ulva
chosen
Ulva is a small, sparsely populated island off the west coast of Scotland, known for its rugged landscapes, wildlife, and historic connections to the Hebrides.
-
B.
Relva
Relva is a civil parish located within the municipality of Ponta Delgada on São Miguel Island in the Azores, Portugal.
-
C.
Velda
Velda is the loyal and resourceful secretary and love interest of private investigator Mike Hammer in the hardboiled crime novel and film "Kiss Me Deadly."
-
D.
Sinnuris
Sinnuris is a town and administrative center located in Egypt’s Faiyum Governorate, known for its agricultural surroundings and proximity to Lake Qarun.
-
E.
Renaelva
Renaelva is a river in eastern Norway that flows through Hedmark county before joining the larger Glomma river.
- 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_69bd43ec4a348190bc41afae43375e71 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd64261af08190b0d5d86b0e7bacc0 |
completed | March 20, 2026, 3:13 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be108bc0048190aeea8674f75105e5 |
completed | March 21, 2026, 3:29 a.m. |
Created at: March 20, 2026, 1:18 p.m.