Triple
T18051568
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jinja |
E431935
|
entity |
| Predicate | usedBy |
P260
|
FINISHED |
| Object |
Airflow
Airflow is an open-source platform for authoring, scheduling, and monitoring complex data workflows as directed acyclic graphs.
|
E1303161
|
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: Airflow | Statement: [Jinja, usedBy, Airflow]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Airflow Context triple: [Jinja, usedBy, Airflow]
-
A.
L’Air
L’Air is a celebrated early 20th-century sculpture by Aristide Maillol that exemplifies his serene, classical approach to the female form.
-
B.
Airai
Airai is a state in the Republic of Palau known for hosting the country’s main international airport and serving as a key gateway to the islands.
-
C.
Breeze
Breeze is a web conferencing and e-learning software platform originally developed by Macromedia for online presentations, training, and collaboration.
-
D.
Luft
Luft is a surname most notably associated with Sid Luft, the American film producer and third husband of entertainer Judy Garland.
-
E.
Aerophile
Aerophile is a company specializing in the design, manufacture, and operation of tethered gas balloons and aerial attractions around the world.
- 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: Airflow Triple: [Jinja, usedBy, Airflow]
Generated description
Airflow is an open-source platform for authoring, scheduling, and monitoring complex data workflows as directed acyclic graphs.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Airflow Target entity description: Airflow is an open-source platform for authoring, scheduling, and monitoring complex data workflows as directed acyclic graphs.
-
A.
L’Air
L’Air is a celebrated early 20th-century sculpture by Aristide Maillol that exemplifies his serene, classical approach to the female form.
-
B.
Airai
Airai is a state in the Republic of Palau known for hosting the country’s main international airport and serving as a key gateway to the islands.
-
C.
Breeze
Breeze is a web conferencing and e-learning software platform originally developed by Macromedia for online presentations, training, and collaboration.
-
D.
Luft
Luft is a surname most notably associated with Sid Luft, the American film producer and third husband of entertainer Judy Garland.
-
E.
Aerophile
Aerophile is a company specializing in the design, manufacture, and operation of tethered gas balloons and aerial attractions around the world.
- 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_69d8b906482481908183315b9ecf9994 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4c0fe4f1881908fa8485cb3ccfa44 |
completed | April 19, 2026, 11:48 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0349bf5fc48190afd460025b1fe505 |
completed | May 12, 2026, 3:39 p.m. |
| NEDg | Description generation | batch_6a034b7197e48190ae62f25f2fb434b6 |
completed | May 12, 2026, 3:46 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a034c08c12081908fee77fbb97b5840 |
completed | May 12, 2026, 3:49 p.m. |
Created at: April 10, 2026, 10:25 a.m.