Triple
T7055809
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stavanger Airport, Sola |
E164087
|
entity |
| Predicate | IATAcode |
P418
|
FINISHED |
| Object |
SVG
SVG is the three-letter IATA airport code assigned to Stavanger Airport, Sola in Norway.
|
E639203
|
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: SVG | Statement: [Stavanger Airport, Sola, IATAcode, SVG]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: SVG Context triple: [Stavanger Airport, Sola, IATAcode, SVG]
-
A.
SVG
SVG (Scalable Vector Graphics) is an XML-based vector image format for two-dimensional graphics that supports interactivity and animation, widely used for web graphics due to its scalability and resolution independence.
-
B.
StarDraw
StarDraw is a vector graphics and diagramming application that was part of the StarOffice productivity suite.
-
C.
Vector Multimedia Extension
Vector Multimedia Extension is a set of SIMD (single instruction, multiple data) instructions for PowerPC processors designed to accelerate multimedia, signal processing, and vector computations.
-
D.
PGF
PGF is the IATA airport code for Perpignan–Rivesaltes Airport in southern France.
-
E.
SmartArt graphics
SmartArt graphics are a collection of pre-designed visual diagrams in Microsoft Office that help users easily illustrate information, processes, and relationships in a polished, professional format.
- 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: SVG Triple: [Stavanger Airport, Sola, IATAcode, SVG]
Generated description
SVG is the three-letter IATA airport code assigned to Stavanger Airport, Sola in Norway.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: SVG Target entity description: SVG is the three-letter IATA airport code assigned to Stavanger Airport, Sola in Norway.
-
A.
SVG
SVG (Scalable Vector Graphics) is an XML-based vector image format for two-dimensional graphics that supports interactivity and animation, widely used for web graphics due to its scalability and resolution independence.
-
B.
StarDraw
StarDraw is a vector graphics and diagramming application that was part of the StarOffice productivity suite.
-
C.
Vector Multimedia Extension
Vector Multimedia Extension is a set of SIMD (single instruction, multiple data) instructions for PowerPC processors designed to accelerate multimedia, signal processing, and vector computations.
-
D.
PGF
PGF is the IATA airport code for Perpignan–Rivesaltes Airport in southern France.
-
E.
SmartArt graphics
SmartArt graphics are a collection of pre-designed visual diagrams in Microsoft Office that help users easily illustrate information, processes, and relationships in a polished, professional format.
- 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_69c68861678881909961ddf4d779f750 |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6e269050c81908c186609a8a7bcf9 |
completed | March 27, 2026, 8:02 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7889ddd488190b1e55828909133eb |
completed | March 28, 2026, 7:51 a.m. |
| NEDg | Description generation | batch_69c78975edf88190b864cd1e3b9622bd |
completed | March 28, 2026, 7:55 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c78bcf02b481908c50e6d7061bbc12 |
completed | March 28, 2026, 8:05 a.m. |
Created at: March 27, 2026, 2:38 p.m.