Triple
T5409656
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | National road 73 |
E120981
|
entity |
| Predicate | connects |
P390
|
FINISHED |
| Object | Nynäshamn |
E143290
|
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: Nynäshamn | Statement: [National road 73, connects, Nynäshamn]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nynäshamn Context triple: [National road 73, connects, Nynäshamn]
-
A.
Kristinehamn
Kristinehamn is a small Swedish town in Värmland County known for its lakeside location on Vänern and its historical role as a regional trading and industrial center.
-
B.
Nynäshamn harbour
chosen
Nynäshamn harbour is a major Swedish port on the Baltic Sea, serving passenger ferries, cruise ships, and cargo traffic south of Stockholm.
-
C.
Nynäshamn Municipality
Nynäshamn Municipality is a coastal municipality in eastern Sweden known for its ferry connections to Gotland and the Baltic states, as well as its scenic archipelago landscapes.
-
D.
Vänersborg
Vänersborg is a Swedish town located at the southern tip of Lake Vänern, known historically as an administrative and trading center.
-
E.
Náströnd
Náströnd is a grim shore in Norse mythology where the souls of the most wicked are punished in a hall woven of serpents and dripping venom.
- 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_69bd463a41cc8190b32ff5af2b96ca93 |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd8796a420819092c1771407cd1a5d |
completed | March 20, 2026, 5:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bf3aa3e1988190ac484c91022dc08b |
completed | March 22, 2026, 12:41 a.m. |
Created at: March 20, 2026, 2:05 p.m.