Triple
T21016715
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ruins of Dorneck Castle |
E517696
|
entity |
| Predicate | heritageDesignation |
P623
|
FINISHED |
| Object |
KGS Inventar A-Objekt
KGS Inventar A-Objekt is a Swiss federal inventory category for cultural properties of national significance.
|
E1462560
|
NE FINISHED |
How this triple was built (4 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: KGS Inventar A-Objekt | Statement: [Ruins of Dorneck Castle, heritageDesignation, KGS Inventar A-Objekt]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: KGS Inventar A-Objekt Context triple: [Ruins of Dorneck Castle, heritageDesignation, KGS Inventar A-Objekt]
-
A.
Kagel
Kagel is a small village in the municipality of Grünheide (Mark) in the Oder-Spree district of Brandenburg, Germany.
-
B.
Kienbaum
Kienbaum is a small village in the municipality of Grünheide (Mark) in Brandenburg, Germany, known in part for its nearby national Olympic training center.
-
C.
KGS
KGS is the IATA airport code for Kos Island International Airport, which serves the Greek island of Kos in the Aegean Sea.
-
D.
KGS
KGS is the official currency code for the Kyrgyzstani som, the national currency of Kyrgyzstan.
-
E.
KG 53
KG 53 was a Luftwaffe bomber wing of Nazi Germany during World War II, known for its operations on both the Eastern and Western Fronts.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: KGS Inventar A-Objekt Triple: [Ruins of Dorneck Castle, heritageDesignation, KGS Inventar A-Objekt]
Generated description
KGS Inventar A-Objekt is a Swiss federal inventory category for cultural properties of national significance.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: KGS Inventar A-Objekt Target entity description: KGS Inventar A-Objekt is a Swiss federal inventory category for cultural properties of national significance.
-
A.
Kagel
Kagel is a small village in the municipality of Grünheide (Mark) in the Oder-Spree district of Brandenburg, Germany.
-
B.
Kienbaum
Kienbaum is a small village in the municipality of Grünheide (Mark) in Brandenburg, Germany, known in part for its nearby national Olympic training center.
-
C.
KGS
KGS is the IATA airport code for Kos Island International Airport, which serves the Greek island of Kos in the Aegean Sea.
-
D.
KGS
KGS is the official currency code for the Kyrgyzstani som, the national currency of Kyrgyzstan.
-
E.
KG 53
KG 53 was a Luftwaffe bomber wing of Nazi Germany during World War II, known for its operations on both the Eastern and Western Fronts.
- F. None of above. chosen
Provenance (5 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_69e0b50262b081909bc488937145eb73 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6fc5968c081909ae6407199858aba |
completed | April 21, 2026, 4:26 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a093b6544ec8190baa55bb07941a231 |
completed | May 17, 2026, 3:52 a.m. |
| NEDg | Description generation | batch_6a093f659a7c8190a10c41821dafacc4 |
completed | May 17, 2026, 4:09 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0940e3b7988190b5400d16211aefcc |
completed | May 17, 2026, 4:15 a.m. |
Created at: April 16, 2026, 1:54 p.m.