Triple
T21003575
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rocky Mountain Construction |
E517354
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object |
Zadra
Zadra is a highly acclaimed hybrid wooden-steel roller coaster in Poland, known for its intense airtime, speed, and innovative design.
|
E1461926
|
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: Zadra | Statement: [Rocky Mountain Construction, notableWork, Zadra]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Zadra Context triple: [Rocky Mountain Construction, notableWork, Zadra]
-
A.
Zadrima
Zadrima is a historical region in northwestern Albania known for its fertile plains, traditional Albanian culture, and proximity to the city of Lezhë.
-
B.
Dzheraśa
Dzheraśa is a figure from Ossetian (Nart) mythology known primarily as the mother of the hero Batraz.
-
C.
Bavadra
Bavadra is a Fijian surname most notably associated with Timoci Bavadra, a former Prime Minister of Fiji.
-
D.
Ádria
Ádria is a given name, primarily used in Portuguese and Spanish-speaking countries, that is a variant of the name Adria.
-
E.
Dausa
Dausa is a town and district headquarters in the Indian state of Rajasthan, known for its historical forts, stepwells, and proximity to Jaipur.
- 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: Zadra Triple: [Rocky Mountain Construction, notableWork, Zadra]
Generated description
Zadra is a highly acclaimed hybrid wooden-steel roller coaster in Poland, known for its intense airtime, speed, and innovative design.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Zadra Target entity description: Zadra is a highly acclaimed hybrid wooden-steel roller coaster in Poland, known for its intense airtime, speed, and innovative design.
-
A.
Zadrima
Zadrima is a historical region in northwestern Albania known for its fertile plains, traditional Albanian culture, and proximity to the city of Lezhë.
-
B.
Dzheraśa
Dzheraśa is a figure from Ossetian (Nart) mythology known primarily as the mother of the hero Batraz.
-
C.
Bavadra
Bavadra is a Fijian surname most notably associated with Timoci Bavadra, a former Prime Minister of Fiji.
-
D.
Ádria
Ádria is a given name, primarily used in Portuguese and Spanish-speaking countries, that is a variant of the name Adria.
-
E.
Dausa
Dausa is a town and district headquarters in the Indian state of Rajasthan, known for its historical forts, stepwells, and proximity to Jaipur.
- 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_69e0b50192308190a284fcc89dd23a49 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6fc3978b0819082b63a98962a673e |
completed | April 21, 2026, 4:25 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a093b563d148190a2c06e8550fa071e |
completed | May 17, 2026, 3:51 a.m. |
| NEDg | Description generation | batch_6a093c1b09708190afd8e748dc4b3888 |
completed | May 17, 2026, 3:55 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a093c885164819093708d94e6fa6f95 |
completed | May 17, 2026, 3:56 a.m. |
Created at: April 16, 2026, 1:52 p.m.