Triple

T7985614
Position Surface form Disambiguated ID Type / Status
Subject Apache Storm E185674 entity
Predicate competesWith P1375 FINISHED
Object Kafka Streams
Kafka Streams is a Java library for building real-time, distributed stream processing applications on top of Apache Kafka.
 E702192 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: Kafka Streams | Statement: [Apache Storm, competesWith, Kafka Streams]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kafka Streams
Context triple: [Apache Storm, competesWith, Kafka Streams]
  • A. Apache Kafka
    Apache Kafka is a distributed event streaming platform widely used for building real-time data pipelines and streaming applications.
  • B. Apache Flink
    Apache Flink is an open-source distributed stream-processing framework designed for high-throughput, low-latency data processing and real-time analytics on large-scale data.
  • C. KSQL
    KSQL is the ICAO airport code for San Carlos Airport, a general aviation facility serving the San Francisco Bay Area in California.
  • D. IBM Streams
    IBM Streams is a high-performance stream processing platform that enables real-time ingestion, analysis, and correlation of large-scale data in motion for enterprise applications.
  • E. Apache Storm
    Apache Storm is a distributed real-time computation system designed for processing large streams of data with low latency and high fault tolerance.
  • 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: Kafka Streams
Triple: [Apache Storm, competesWith, Kafka Streams]
Generated description
Kafka Streams is a Java library for building real-time, distributed stream processing applications on top of Apache Kafka.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kafka Streams
Target entity description: Kafka Streams is a Java library for building real-time, distributed stream processing applications on top of Apache Kafka.
  • A. Apache Kafka
    Apache Kafka is a distributed event streaming platform widely used for building real-time data pipelines and streaming applications.
  • B. Apache Flink
    Apache Flink is an open-source distributed stream-processing framework designed for high-throughput, low-latency data processing and real-time analytics on large-scale data.
  • C. KSQL
    KSQL is the ICAO airport code for San Carlos Airport, a general aviation facility serving the San Francisco Bay Area in California.
  • D. IBM Streams
    IBM Streams is a high-performance stream processing platform that enables real-time ingestion, analysis, and correlation of large-scale data in motion for enterprise applications.
  • E. Apache Storm
    Apache Storm is a distributed real-time computation system designed for processing large streams of data with low latency and high fault tolerance.
  • 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_69ca829a2cfc819083d591d58ec04075 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb3c4a55b881909a96133e56c0dffa completed March 31, 2026, 3:15 a.m.
NED1 Entity disambiguation (via context triple) batch_69cbe0e6f3c48190a0132fa90eec6420 completed March 31, 2026, 2:57 p.m.
NEDg Description generation batch_69cbe43e47048190a0044477f88de5d0 completed March 31, 2026, 3:11 p.m.
NED2 Entity disambiguation (via description) batch_69cc0d60254c819087d1de7ca6ea554b completed March 31, 2026, 6:07 p.m.
Created at: March 30, 2026, 5:15 p.m.