Triple
T15593423
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nokia N78 |
E374806
|
entity |
| Predicate | hasFeature |
P182
|
FINISHED |
| Object | Nokia Maps |
E282150
|
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: Nokia Maps | Statement: [Nokia N78, hasFeature, Nokia Maps]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nokia Maps Context triple: [Nokia N78, hasFeature, Nokia Maps]
-
A.
Nokia HERE Maps
chosen
Nokia HERE Maps is a mapping and navigation service offering offline maps, turn-by-turn directions, and location-based features across multiple devices and platforms.
-
B.
Baidu Maps
Baidu Maps is a Chinese web mapping and navigation service offering detailed maps, real-time traffic, and location-based services primarily for users in China.
-
C.
Yandex Maps
Yandex Maps is a Russian online mapping and navigation service offering detailed maps, satellite imagery, route planning, and real-time traffic information across numerous regions.
-
D.
Maps.me
Maps.me is a mobile navigation app that provides offline maps and routing based on OpenStreetMap data.
-
E.
MapKit
MapKit is an Apple framework that enables developers to embed interactive maps and location-based features into their iOS, macOS, watchOS, and tvOS applications.
- 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_69d85cce25008190b13b52745fbd719b |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04e5e43d48190a8fd367f13f1c7e1 |
completed | April 16, 2026, 2:50 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff56c7db58819089cb488fb3ea96cd |
completed | May 9, 2026, 3:46 p.m. |
Created at: April 10, 2026, 4:12 a.m.