Triple
T20041703
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Philippsburg fortress |
E497435
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Speyer |
—
|
NE NERFINISHED |
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: Speyer | Statement: [Philippsburg fortress, near, Speyer]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Speyer Context triple: [Philippsburg fortress, near, Speyer]
-
A.
Speyer
chosen
Speyer is a historic city in southwestern Germany on the Rhine River, renowned for its Romanesque imperial cathedral, a UNESCO World Heritage Site.
-
B.
Trier
Trier is a historic city in western Germany, renowned as one of the country’s oldest cities with extensive Roman ruins and medieval landmarks.
-
C.
Mainz
Mainz is a historic German city on the Rhine River known as a major ecclesiastical and political center of the Holy Roman Empire and today as the capital of the state of Rhineland-Palatinate.
-
D.
Lingolsheim
Lingolsheim is a suburban commune in northeastern France, located just southwest of Strasbourg in the Grand Est region.
-
E.
Saarbrücken
Saarbrücken is a German city on the Saar River known as an industrial, cultural, and educational center near the French border.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69da627278c88190babe4297a9df1236 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e662eb9a6081909d06dc1d457b4d5a |
completed | April 20, 2026, 5:31 p.m. |
Created at: April 11, 2026, 3:37 p.m.