Triple
T5176644
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tvärbanan |
E116814
|
entity |
| Predicate | hasTerminus |
P388
|
FINISHED |
| Object | Alvik |
E379961
|
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: Alvik | Statement: [Tvärbanan, hasTerminus, Alvik]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Alvik Context triple: [Tvärbanan, hasTerminus, Alvik]
-
A.
Alvik
chosen
Alvik is a district in western Stockholm known as a key public transport hub, particularly for its tram and metro connections.
-
B.
Larsmo
Larsmo is a coastal municipality in western Finland known for its archipelago and Swedish-speaking majority population.
-
C.
Arve
The Arve is a river in southwestern Switzerland and southeastern France that flows through Geneva before joining the Rhône.
-
D.
Avsola
Avsola is a biosimilar monoclonal antibody to infliximab used to treat various autoimmune inflammatory conditions.
-
E.
Givors
Givors is a commune in eastern France located in the Metropolis of Lyon, known historically as an industrial and river-port town on the Rhône.
- 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_69bd446140f08190becb93c61158f27f |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd7974a5308190819b100e07189131 |
completed | March 20, 2026, 4:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bed94e269481908118fd1af1fc6a44 |
completed | March 21, 2026, 5:45 p.m. |
Created at: March 20, 2026, 1:45 p.m.