Triple
T3788348
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | National Ski Jumping Centre |
E85582
|
entity |
| Predicate | hasKPoint |
P15212
|
FINISHED |
| Object |
K95
K95 is a ski jumping hill size classification indicating a normal hill with a K-point of 95 meters, commonly used in competitive ski jumping events.
|
E389365
|
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: K95 | Statement: [National Ski Jumping Centre, hasKPoint, K95]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: K95 Context triple: [National Ski Jumping Centre, hasKPoint, K95]
-
A.
K9K
K9K is a Canadian postal code prefix assigned to part of the city of Peterborough in Ontario.
-
B.
K9A1
K9A1 is an upgraded South Korean K9 Thunder self-propelled howitzer variant featuring improved fire control, automation, and crew ergonomics.
-
C.
K5
K5 is an alternative name for Gasherbrum I, one of the world’s highest and most challenging eight-thousander peaks in the Karakoram range.
-
D.
K9A2
K9A2 is an advanced, upgraded version of the South Korean K9 Thunder self-propelled howitzer, featuring enhanced automation, improved fire control, and greater operational efficiency.
-
E.
C595
C595 is the designation for an ASTM standard specification covering blended hydraulic cements used in construction.
- 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: K95 Triple: [National Ski Jumping Centre, hasKPoint, K95]
Generated description
K95 is a ski jumping hill size classification indicating a normal hill with a K-point of 95 meters, commonly used in competitive ski jumping events.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: K95 Target entity description: K95 is a ski jumping hill size classification indicating a normal hill with a K-point of 95 meters, commonly used in competitive ski jumping events.
-
A.
K9K
K9K is a Canadian postal code prefix assigned to part of the city of Peterborough in Ontario.
-
B.
K9A1
K9A1 is an upgraded South Korean K9 Thunder self-propelled howitzer variant featuring improved fire control, automation, and crew ergonomics.
-
C.
K5
K5 is an alternative name for Gasherbrum I, one of the world’s highest and most challenging eight-thousander peaks in the Karakoram range.
-
D.
K9A2
K9A2 is an advanced, upgraded version of the South Korean K9 Thunder self-propelled howitzer, featuring enhanced automation, improved fire control, and greater operational efficiency.
-
E.
C595
C595 is the designation for an ASTM standard specification covering blended hydraulic cements used in construction.
- 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_69aed937fa8881908208ef3801060826 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aee42f4dd08190be10d0113aab4249 |
completed | March 9, 2026, 3:15 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b4f05031cc8190825105f77dd76438 |
completed | March 14, 2026, 5:21 a.m. |
| NEDg | Description generation | batch_69b4f4f80f4c8190890dae6770d10d4d |
completed | March 14, 2026, 5:41 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b4f55f53ec8190a5f9cf6d494e75dd |
completed | March 14, 2026, 5:42 a.m. |
Created at: March 9, 2026, 3:13 p.m.