Triple
T21007582
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Grödig |
E517452
|
entity |
| Predicate | hasSubdivision |
P747
|
FINISHED |
| Object | St. Leonhard |
E451551
|
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: St. Leonhard | Statement: [Grödig, hasSubdivision, St. Leonhard]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: St. Leonhard Context triple: [Grödig, hasSubdivision, St. Leonhard]
-
A.
St. Leonhard
chosen
St. Leonhard is a locality near Salzburg, Austria, known as the valley station area for the Untersbergbahn cable car that ascends the Untersberg mountain.
-
B.
Saint Pölten
Saint Pölten is an Austrian football club based in the city of Sankt Pölten, known for competing in the country’s professional league system.
-
C.
St. Kajetan
St. Kajetan is the common name for the Theatinerkirche, a prominent Baroque Catholic church in Munich, Germany.
-
D.
Sankt Heinrich
Sankt Heinrich is a small village in Bavaria, Germany, that forms part of the municipality of Münsing near Lake Starnberg.
-
E.
St. Koloman
St. Koloman is a small Austrian municipality in the Tennengau region of Salzburg, known for its alpine scenery and traditional rural character.
- 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_69e0b50192308190a284fcc89dd23a49 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6fc3cc8648190b1a419ef734a69e6 |
completed | April 21, 2026, 4:25 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a093b5c418c81908f54334092d5759a |
completed | May 17, 2026, 3:51 a.m. |
Created at: April 16, 2026, 1:53 p.m.