Triple
T16089478
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Line A (Prague Metro) |
E390322
|
entity |
| Predicate | hasStation |
P35
|
FINISHED |
| Object |
Flora
Flora is a Prague Metro station on Line A serving the Vinohrady district and connected to the Atrium Flora shopping center.
|
E1192853
|
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: Flora | Statement: [Line A (Prague Metro), hasStation, Flora]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Flora Context triple: [Line A (Prague Metro), hasStation, Flora]
-
A.
Flora
Flora is a symbolist painting by Evelyn De Morgan depicting the Roman goddess of flowers and spring in a richly allegorical, Pre-Raphaelite-inspired style.
-
B.
Flora
Flora is the young niece in Henry James's novella "The Turn of the Screw," whose eerie innocence and ambiguous relationship to the supernatural are central to the story's psychological horror.
-
C.
Flora
Flora is the middle name of Ruth Disney, the daughter of Walt Disney and his wife Lillian.
-
D.
Flora
Flora is a popular brand of margarine and other spreadable food products owned by Upfield and marketed for heart health and everyday cooking.
-
E.
Flora
Flora is one of the three good fairies who serve as royal advisors and magical guardians in the animated children's series "Sofia the First."
- 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: Flora Triple: [Line A (Prague Metro), hasStation, Flora]
Generated description
Flora is a Prague Metro station on Line A serving the Vinohrady district and connected to the Atrium Flora shopping center.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Flora Target entity description: Flora is a Prague Metro station on Line A serving the Vinohrady district and connected to the Atrium Flora shopping center.
-
A.
Flora
Flora is a rural municipality in the province of Apayao in the Cordillera Administrative Region of the Philippines.
-
B.
Flora
Flora is a feminine given name of Latin origin meaning "flower," historically associated with the Roman goddess of flowers and spring.
-
C.
Flora
Flora is a symbolist painting by Evelyn De Morgan depicting the Roman goddess of flowers and spring in a richly allegorical, Pre-Raphaelite-inspired style.
-
D.
Flora
Flora is a popular brand of margarine and other spreadable food products owned by Upfield and marketed for heart health and everyday cooking.
-
E.
Flora
Flora is one of the three good fairies in Disney's "Sleeping Beauty," known for her red attire, leadership among the fairies, and role in protecting Princess Aurora.
- 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_69d87f198bc48190a8b7e53ca15b7ead |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e1845161908190adca2af94710b2cc |
completed | April 17, 2026, 12:52 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffe490d494819081f812811f032702 |
completed | May 10, 2026, 1:51 a.m. |
| NEDg | Description generation | batch_69ffe63f757c81908c7dc3c5ae3075c6 |
completed | May 10, 2026, 1:58 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ffe6b3f25481908dd4b6108b5d95c0 |
completed | May 10, 2026, 2 a.m. |
Created at: April 10, 2026, 4:59 a.m.