Triple

T17234343
Position Surface form Disambiguated ID Type / Status
Subject Chrome Web Platform features E418320 entity
Predicate includesAPI P126488 FINISHED
Object Streams API E856192 NE FINISHED

How this triple was built (2 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: Streams API | Statement: [Chrome Web Platform features, includesAPI, Streams API]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Streams API
Context triple: [Chrome Web Platform features, includesAPI, Streams API]
  • A. Streams API chosen
    The Streams API is a web platform feature that enables efficient, programmable handling of streaming data in JavaScript, allowing developers to read, write, and transform data chunks incrementally.
  • B. DataStream API
    DataStream API is Apache Flink’s core streaming abstraction for building stateful, event-driven data processing applications over unbounded and bounded data streams.
  • C. Kafka Streams
    Kafka Streams is a Java library for building real-time, distributed stream processing applications on top of Apache Kafka.
  • D. Reactive Streams
    Reactive Streams is a standard for asynchronous stream processing with non-blocking back pressure, designed to enable interoperable reactive programming across different libraries and runtimes.
  • E. Akka Streams
    Akka Streams is a library for building and running asynchronous, backpressure-aware data processing pipelines on the JVM, based on the Reactive Streams specification.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d886d8e96081909870bff6c3d0bf09 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e42dfa0a408190880804d463305867 completed April 19, 2026, 1:20 a.m.
NED1 Entity disambiguation (via context triple) batch_6a01676382388190ab82bd10bd53f59e completed May 11, 2026, 5:21 a.m.
Created at: April 10, 2026, 5:39 a.m.