Triple
T23456909
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stubbenkammer |
E567949
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Kleine Stubbenkammer |
—
|
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: Kleine Stubbenkammer | Statement: [Stubbenkammer, hasPart, Kleine Stubbenkammer]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kleine Stubbenkammer Context triple: [Stubbenkammer, hasPart, Kleine Stubbenkammer]
-
A.
Stubbenkammer
chosen
Stubbenkammer is a famous chalk cliff formation on the island of Rügen in Germany, known for its dramatic white cliffs overlooking the Baltic Sea.
-
B.
Fernerstube
Fernerstube is a glacier located on the slopes of the Zuckerhütl peak in the Stubai Alps of Tyrol, Austria.
-
C.
Der Keller
Der Keller is an autobiographical work by Austrian writer Thomas Bernhard, depicting his youth and formative experiences working in a grocery cellar in postwar Salzburg.
-
D.
الحجرات
الحجرات هي سورة مدنية في القرآن الكريم تُعنى بآداب التعامل الاجتماعي وضبط السلوك بين المسلمين.
-
E.
Herzgruft
Herzgruft is the burial chamber in Vienna where the hearts of many members of the Habsburg royal family are interred.
- 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_69e2458b4c888190b1d7998f9862a558 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f1a6980d4481909fab47cb5bd28eab |
completed | April 29, 2026, 6:35 a.m. |
Created at: April 17, 2026, 5:53 p.m.