Triple
T2055609
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saalburg Roman fort |
E45665
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Taunus |
E97286
|
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: Taunus | Statement: [Saalburg Roman fort, locatedIn, Taunus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Taunus Context triple: [Saalburg Roman fort, locatedIn, Taunus]
-
A.
Taunus
chosen
Taunus is a low mountain range in central Germany known for its forested hills, spa towns, and proximity to the Rhine-Main metropolitan region.
-
B.
Ehrwald
Ehrwald is a picturesque Austrian village in Tyrol, known as a popular alpine resort and gateway to the Zugspitze massif.
-
C.
Velkua
Velkua is a former island municipality in southwestern Finland known for its coastal archipelago landscape in the Baltic Sea.
-
D.
Tauresium
Tauresium was an ancient settlement in the Balkans, traditionally identified as the birthplace of the Byzantine emperor Justinian I.
-
E.
Viadrus
Viadrus is the ancient Latin name historically used to refer to the Oder River in Central Europe.
- 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_69a8891a19508190a12ef1e192308dcb |
completed | March 4, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69abb9a9ce548190a5a3488fafb2e79e |
completed | March 7, 2026, 5:37 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae200eb09881908bbfe47ebb62f55e |
completed | March 9, 2026, 1:19 a.m. |
Created at: March 4, 2026, 7:40 p.m.