Triple

T12323388
Position Surface form Disambiguated ID Type / Status
Subject Amazon Neptune E293773 entity
Predicate supportsQueryLanguage P203 FINISHED
Object Apache TinkerPop Gremlin
Apache TinkerPop Gremlin is a graph traversal language and virtual machine used for querying and manipulating property graphs across various graph databases and frameworks.
E975101 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: Apache TinkerPop Gremlin | Statement: [Amazon Neptune, supportsQueryLanguage, Apache TinkerPop Gremlin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Apache TinkerPop Gremlin
Context triple: [Amazon Neptune, supportsQueryLanguage, Apache TinkerPop Gremlin]
  • A. GraphX
    GraphX is Apache Spark’s distributed graph processing framework that enables large-scale graph computation and analysis using Spark’s resilient distributed datasets (RDDs).
  • B. Oracle Spatial and Graph stack
    Oracle Spatial and Graph stack is an Oracle Database feature set that provides advanced spatial data management, geospatial analytics, and graph processing capabilities for building location-aware and network-centric applications.
  • C. Amazon Neptune
    Amazon Neptune is a fully managed graph database service designed for storing and querying highly connected data using popular graph models and query languages.
  • D. CyberGraphX
    CyberGraphX is a graphics subsystem and API originally developed for Amiga systems, providing advanced graphics card support and hardware-accelerated rendering.
  • E. Blazegraph
    Blazegraph is an open-source, high-performance graph database and triplestore engine designed for large-scale RDF data and SPARQL querying.
  • 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: Apache TinkerPop Gremlin
Triple: [Amazon Neptune, supportsQueryLanguage, Apache TinkerPop Gremlin]
Generated description
Apache TinkerPop Gremlin is a graph traversal language and virtual machine used for querying and manipulating property graphs across various graph databases and frameworks.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Apache TinkerPop Gremlin
Target entity description: Apache TinkerPop Gremlin is a graph traversal language and virtual machine used for querying and manipulating property graphs across various graph databases and frameworks.
  • A. GraphX
    GraphX is Apache Spark’s distributed graph processing framework that enables large-scale graph computation and analysis using Spark’s resilient distributed datasets (RDDs).
  • B. Oracle Spatial and Graph stack
    Oracle Spatial and Graph stack is an Oracle Database feature set that provides advanced spatial data management, geospatial analytics, and graph processing capabilities for building location-aware and network-centric applications.
  • C. Amazon Neptune
    Amazon Neptune is a fully managed graph database service designed for storing and querying highly connected data using popular graph models and query languages.
  • D. CyberGraphX
    CyberGraphX is a graphics subsystem and API originally developed for Amiga systems, providing advanced graphics card support and hardware-accelerated rendering.
  • E. Blazegraph
    Blazegraph is an open-source, high-performance graph database and triplestore engine designed for large-scale RDF data and SPARQL querying.
  • 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_69d6ab6ae0dc8190b1522a9c1c55c114 completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d93f4d7dac81909ff10e64e229ef33 completed April 10, 2026, 6:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69f61e8d27288190bdf32acd600141db completed May 2, 2026, 3:55 p.m.
NEDg Description generation batch_69f61f9493d081909a543bcafeb508d1 completed May 2, 2026, 4 p.m.
NED2 Entity disambiguation (via description) batch_69f620ad9ec0819099909142fbad6412 completed May 2, 2026, 4:05 p.m.
Created at: April 8, 2026, 9:53 p.m.