Triple
T16038997
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Iller |
E389043
|
entity |
| Predicate | flowsThrough |
P225
|
FINISHED |
| Object | Oberstdorf |
E231237
|
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: Oberstdorf | Statement: [Iller, flowsThrough, Oberstdorf]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Oberstdorf Context triple: [Iller, flowsThrough, Oberstdorf]
-
A.
Oberstdorf
chosen
Oberstdorf is a renowned alpine resort town in southern Germany known for skiing, ski jumping, and hiking amid dramatic mountain scenery.
-
B.
Oberndorf am Lech
Oberndorf am Lech is a Bavarian municipality in southern Germany situated along the River Lech.
-
C.
Igls
Igls is an Austrian alpine village near Innsbruck known for its winter sports facilities and role in hosting Olympic events.
-
D.
Oberndorf bei Salzburg
Oberndorf bei Salzburg is a small Austrian town near Salzburg, best known as the place where the Christmas carol "Silent Night" was first performed.
-
E.
Garmisch-Partenkirchen
Garmisch-Partenkirchen is a renowned Bavarian alpine town in southern Germany, famous for skiing, winter sports, and its picturesque mountain scenery.
- 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_69d86dada3808190825d5f80d72fbe88 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e1833eb90c8190b10dca3ce0793ddf |
completed | April 17, 2026, 12:47 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffdbd5acb48190a10e40074fffd425 |
completed | May 10, 2026, 1:13 a.m. |
Created at: April 10, 2026, 4:56 a.m.