Triple
T12914749
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | KSQL |
E308947
|
entity |
| Predicate | hasICAOCode |
P419
|
FINISHED |
| Object | KSQL |
E308947
|
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: KSQL | Statement: [KSQL, hasICAOCode, KSQL]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: KSQL Context triple: [KSQL, hasICAOCode, KSQL]
-
A.
KSQL
chosen
KSQL is the ICAO airport code for San Carlos Airport, a general aviation facility serving the San Francisco Bay Area in California.
-
B.
Kafka Streams
Kafka Streams is a Java library for building real-time, distributed stream processing applications on top of Apache Kafka.
-
C.
BlazingSQL
BlazingSQL is an open-source SQL engine that enables GPU-accelerated data processing and analytics, often used within the NVIDIA RAPIDS ecosystem for high-performance query execution on large datasets.
-
D.
Kusto Query Language
Kusto Query Language is a powerful, read-only query language designed by Microsoft for interactive analytics over large volumes of structured, semi-structured, and time-series data in Azure services.
-
E.
CQL
CQL (Contextual Query Language) is a formal query language designed for representing and expressing complex search queries in a human-readable, standards-based way, commonly used in information retrieval and library systems.
- 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_69d7bdf92b588190acdf2a2291ac4590 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d971a0d6508190bca9668e9e06abfe |
completed | April 10, 2026, 9:54 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6a56ea03c819093a5b8657e27768e |
completed | May 3, 2026, 1:31 a.m. |
Created at: April 9, 2026, 5:41 p.m.