Triple
T17561368
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Apache Beam |
E427701
|
entity |
| Predicate | supportsRunner |
P127972
|
FINISHED |
| Object |
DirectRunner
DirectRunner is Apache Beam’s local, in-memory runner used primarily for development, testing, and debugging Beam pipelines without requiring an external distributed processing engine.
|
E427701
|
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: DirectRunner | Statement: [Apache Beam, supportsRunner, DirectRunner]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: DirectRunner Context triple: [Apache Beam, supportsRunner, DirectRunner]
-
A.
Mono runtime
Mono runtime is an open-source implementation of Microsoft’s .NET framework that enables cross-platform execution of .NET applications on systems such as Linux, macOS, and mobile devices.
-
B.
Google Cloud Dataflow
Google Cloud Dataflow is a fully managed service for developing and executing batch and streaming data processing pipelines, based on Apache Beam, within the Google Cloud ecosystem.
-
C.
Apache Beam
Apache Beam is an open-source unified programming model for defining and executing batch and streaming data processing pipelines across multiple execution engines.
-
D.
Apache Gobblin
Apache Gobblin is an open-source distributed data integration framework designed for large-scale data ingestion, replication, and lifecycle management across diverse data sources and sinks.
-
E.
Horovod
Horovod is an open-source distributed deep learning framework designed to make training models across multiple GPUs and machines fast and easy.
- 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: DirectRunner Triple: [Apache Beam, supportsRunner, DirectRunner]
Generated description
DirectRunner is Apache Beam’s local, in-memory runner used primarily for development, testing, and debugging Beam pipelines without requiring an external distributed processing engine.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: DirectRunner Target entity description: DirectRunner is Apache Beam’s local, in-memory runner used primarily for development, testing, and debugging Beam pipelines without requiring an external distributed processing engine.
-
A.
Mono runtime
Mono runtime is an open-source implementation of Microsoft’s .NET framework that enables cross-platform execution of .NET applications on systems such as Linux, macOS, and mobile devices.
-
B.
Google Cloud Dataflow
Google Cloud Dataflow is a fully managed service for developing and executing batch and streaming data processing pipelines, based on Apache Beam, within the Google Cloud ecosystem.
-
C.
Apache Beam
chosen
Apache Beam is an open-source unified programming model for defining and executing batch and streaming data processing pipelines across multiple execution engines.
-
D.
Apache Gobblin
Apache Gobblin is an open-source distributed data integration framework designed for large-scale data ingestion, replication, and lifecycle management across diverse data sources and sinks.
-
E.
Horovod
Horovod is an open-source distributed deep learning framework designed to make training models across multiple GPUs and machines fast and easy.
- F. None of above.
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_69d889e0385081908a04b66f4dd4bd0d |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e456274c888190ac80402e391674dd |
completed | April 19, 2026, 4:12 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a01d29694a8819095351b929cfaf324 |
completed | May 11, 2026, 12:59 p.m. |
| NEDg | Description generation | batch_6a01d4436b448190bff8710eac0ce569 |
completed | May 11, 2026, 1:06 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a01d49cb9c081908b07b87ec3b2a133 |
completed | May 11, 2026, 1:07 p.m. |
Created at: April 10, 2026, 5:50 a.m.