Triple
T5244327
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Olympiapark |
E118420
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object |
Olympiaberg
Olympiaberg is an artificial hill in Munich, Germany, created from World War II rubble and now a popular vantage point within the city’s Olympic Park.
|
E504714
|
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: Olympiaberg | Statement: [Olympiapark, hasPart, Olympiaberg]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Olympiaberg Context triple: [Olympiapark, hasPart, Olympiaberg]
-
A.
Valberg
Valberg is a popular ski resort village in the southern French Alps known for its family-friendly slopes and sunny Mediterranean-alpine climate.
-
B.
Brocken
Brocken is a prominent mountain in central Germany’s Harz range, known for its harsh climate, folklore, and role in literature and cultural history.
-
C.
Bärenkopf
Bärenkopf is a mountain peak in the Austrian Alps that forms part of the Glockner Group.
-
D.
Rigi massif
Rigi massif is a prominent mountain group in central Switzerland, famed for its panoramic views over surrounding lakes and the Alps and often called the “Queen of the Mountains.”
-
E.
Alsberg
Alsberg is a surname of Germanic origin borne by various notable individuals, including American writer and theater director Henry Alsberg.
- 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: Olympiaberg Triple: [Olympiapark, hasPart, Olympiaberg]
Generated description
Olympiaberg is an artificial hill in Munich, Germany, created from World War II rubble and now a popular vantage point within the city’s Olympic Park.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Olympiaberg Target entity description: Olympiaberg is an artificial hill in Munich, Germany, created from World War II rubble and now a popular vantage point within the city’s Olympic Park.
-
A.
Valberg
Valberg is a popular ski resort village in the southern French Alps known for its family-friendly slopes and sunny Mediterranean-alpine climate.
-
B.
Brocken
Brocken is a prominent mountain in central Germany’s Harz range, known for its harsh climate, folklore, and role in literature and cultural history.
-
C.
Bärenkopf
Bärenkopf is a mountain peak in the Austrian Alps that forms part of the Glockner Group.
-
D.
Rigi massif
Rigi massif is a prominent mountain group in central Switzerland, famed for its panoramic views over surrounding lakes and the Alps and often called the “Queen of the Mountains.”
-
E.
Alsberg
Alsberg is a surname of Germanic origin borne by various notable individuals, including American writer and theater director Henry Alsberg.
- 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_69bd4468aacc8190a8196f71855cdf4f |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd7b4fa0ec8190bce3da09aa768726 |
completed | March 20, 2026, 4:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bef82f2738819080c5a0963f6dbbb0 |
completed | March 21, 2026, 7:57 p.m. |
| NEDg | Description generation | batch_69bef909df208190b96b2a7a4a404f69 |
completed | March 21, 2026, 8:01 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69bef96ed108819084cc9e44ae415a6d |
completed | March 21, 2026, 8:02 p.m. |
Created at: March 20, 2026, 1:49 p.m.