Triple
T13861794
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Loisach |
E333213
|
entity |
| Predicate | flowsInto |
P408
|
FINISHED |
| Object | Isar at Wolfratshausen |
E66587
|
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: Isar at Wolfratshausen | Statement: [Loisach, flowsInto, Isar at Wolfratshausen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Isar at Wolfratshausen Context triple: [Loisach, flowsInto, Isar at Wolfratshausen]
-
A.
Bad Reichenhall
Bad Reichenhall is a Bavarian spa town in southeastern Germany, renowned for its alpine setting and historic salt production.
-
B.
Isar
chosen
The Isar is a major river in the Austrian and German Alps that flows through cities such as Munich before joining the Danube.
-
C.
Isar
Isar is a structured, human-readable proof language designed for writing formal proofs within the Isabelle interactive theorem prover.
-
D.
Gundremmingen
Gundremmingen is a small Bavarian municipality best known for hosting one of Germany’s major nuclear power plants.
-
E.
Würzburg Riese
Würzburg Riese was a larger, more powerful German World War II ground-based radar system used primarily for air defense and gun-laying.
- 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_69d81c5ced9c8190b0e9bcc6effe5959 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de05c20db88190acb842748aa01039 |
completed | April 14, 2026, 9:15 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7c0ff1f78819088ae58f703e2c9ff |
completed | May 3, 2026, 9:41 p.m. |
Created at: April 9, 2026, 10:14 p.m.