Triple
T13799898
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ullevi tram stops |
E331611
|
entity |
| Predicate | serves |
P98
|
FINISHED |
| Object | Ullevi stadium area |
E66012
|
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: Ullevi stadium area | Statement: [Ullevi tram stops, serves, Ullevi stadium area]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ullevi stadium area Context triple: [Ullevi tram stops, serves, Ullevi stadium area]
-
A.
Ullevi Stadium
chosen
Ullevi Stadium is a major multi-purpose arena in Gothenburg, Sweden, known for hosting large football matches, athletics events, and concerts.
-
B.
Aker Stadion
Aker Stadion is a football stadium in Molde, Norway, best known as the home ground of the Norwegian club Molde FK.
-
C.
Viking Stadion
Viking Stadion is a football stadium in Stavanger, Norway, primarily serving as the home ground of Viking FK.
-
D.
Vålerenga Stadion
Vålerenga Stadion is a football stadium in Oslo, Norway, serving as the home ground of the Vålerenga Fotball club.
-
E.
Daknamstadion
Daknamstadion is a football stadium in Lokeren, Belgium, best known as the long-time home ground of K.S.C. Lokeren Oost-Vlaanderen.
- 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_69d81c58feb08190a77bca8bf7d6d20f |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de025ce9148190b23370f6a522ff7a |
completed | April 14, 2026, 9:01 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7b8da594c81908cb878a8cc1b3a72 |
completed | May 3, 2026, 9:06 p.m. |
Created at: April 9, 2026, 10:11 p.m.