Triple
T7508048
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nesoddtangen peninsula |
E177442
|
entity |
| Predicate | hasFrequentServiceTo |
P6787
|
FINISHED |
| Object | Oslo |
E3654
|
NE FINISHED |
How this triple was built (3 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: Oslo | Statement: [Nesoddtangen peninsula, hasFrequentServiceTo, Oslo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Oslo Context triple: [Nesoddtangen peninsula, hasFrequentServiceTo, Oslo]
-
A.
Oslo
chosen
Oslo is the capital and largest city of Norway, known as a major cultural, economic, and governmental center.
-
B.
Trondheim
Trondheim is a historic Norwegian city in Trøndelag county, known for its medieval Nidaros Cathedral and role as a former capital of Norway.
-
C.
Bergen
Bergen is a city in western Germany, historically notable as the site of the 1759 Battle of Bergen during the Seven Years' War.
-
D.
Bergen
Bergen is Norway's second-largest city, renowned for its historic harbor, surrounding mountains and fjords, and role as a former Hanseatic trading hub.
-
E.
Bergens
The Bergens are a race of gloomy, troll-eating creatures who serve as the primary villains in the animated film "Trolls."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFrequentServiceTo Context triple: [Nesoddtangen peninsula, hasFrequentServiceTo, Oslo]
-
A.
hasServiceTo
chosen
Indicates that one entity provides, offers, or operates a service for or directed toward another entity.
-
B.
hasFrequentActivity
Indicates that an entity regularly engages in or exhibits a high level of a particular activity over a given period.
-
C.
isFrequently
Indicates that an action, state, or relationship occurs often or with high regularity between the related entities.
-
D.
hasConstituentServicesIn
Indicates that an entity provides constituent services within a specified geographic or jurisdictional area.
-
E.
serviceFrequencyContext
Indicates the contextual conditions or circumstances under which a service’s frequency is defined, applied, or interpreted.
- F. None of above.
Provenance (4 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_69c69f276b108190af2cc790b6554544 |
completed | March 27, 2026, 3:15 p.m. |
| NER | Named-entity recognition | batch_69c6f5b8ab5c8190828ee8d144068828 |
completed | March 27, 2026, 9:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c8569b932481909d41130303e21518 |
completed | March 28, 2026, 10:30 p.m. |
| PD | Predicate disambiguation | batch_69c6f4d44e9481909813e073b194f6f4 |
completed | March 27, 2026, 9:21 p.m. |
Created at: March 27, 2026, 3:45 p.m.