Triple
T8929947
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vabis |
E212626
|
entity |
| Predicate | successor |
P78
|
FINISHED |
| Object | Scania-Vabis |
E37748
|
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: Scania-Vabis | Statement: [Vabis, successor, Scania-Vabis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Scania-Vabis Context triple: [Vabis, successor, Scania-Vabis]
-
A.
Scania
chosen
Scania is a Swedish manufacturer renowned for its heavy trucks, buses, and industrial and marine engines.
-
B.
Scania
Scania is a historical province in southern Sweden known for its fertile farmland, coastal landscapes, and former status as part of Denmark.
-
C.
Neoplan
Neoplan is a German bus and coach manufacturer renowned for its innovative, high-end touring and city buses.
-
D.
Saab Kockums
Saab Kockums is a Swedish shipyard and defense company best known for designing and building advanced submarines and naval vessels.
-
E.
Volvo RM8
The Volvo RM8 is a Swedish afterburning turbofan jet engine developed from the Pratt & Whitney JT8D to power the Saab 37 Viggen fighter aircraft.
- 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_69ca8395c438819087d7cb844ab5990c |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc6676d5d881908ce78cbb5561a68b |
completed | April 1, 2026, 12:27 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfdb856560819085132abe9ef94819 |
completed | April 3, 2026, 3:23 p.m. |
Created at: March 30, 2026, 6:57 p.m.