Triple
T15656101
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sandvesanden beach |
E376444
|
entity |
| Predicate | nearbySettlement |
P350
|
FINISHED |
| Object | Sandve |
E376435
|
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: Sandve | Statement: [Sandvesanden beach, nearbySettlement, Sandve]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sandve Context triple: [Sandvesanden beach, nearbySettlement, Sandve]
-
A.
Sandve
chosen
Sandve is a small coastal village in Karmøy municipality in Rogaland county, southwestern Norway.
-
B.
Saane
The Saane, also known as the Sarine, is a major river in western Switzerland that flows through the canton of Fribourg before joining the Aare.
-
C.
Sandvollan
Sandvollan is a village in the municipality of Inderøy in Trøndelag county, Norway.
-
D.
Sveg
Sveg is a small town in central Sweden known as an administrative and service hub in the sparsely populated province of Härjedalen.
-
E.
Sandeen
Sandeen is a surname most notably associated with Cathy A. Sandeen, an American academic administrator and university leader.
- 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_69d85cd1564c8190991adda63bfab4b0 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04ef1f83c8190bbf65eed162cbd55 |
completed | April 16, 2026, 2:52 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff67994fbc819090f2da267888e8fb |
completed | May 9, 2026, 4:58 p.m. |
Created at: April 10, 2026, 4:15 a.m.