Triple
T19825724
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sumburgh Airport |
E476319
|
entity |
| Predicate | IATACode |
P418
|
FINISHED |
| Object | LSI |
—
|
NE NERFINISHED |
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: LSI | Statement: [Sumburgh Airport, IATACode, LSI]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: LSI Context triple: [Sumburgh Airport, IATACode, LSI]
-
A.
LSI
chosen
LSI is the three-letter IATA airport code for Sumburgh Airport in the Shetland Islands, Scotland.
-
B.
LSI
LSI is the commonly used abbreviation for the Linguistic Survey of India, a comprehensive survey documenting the languages and dialects spoken across the Indian subcontinent.
-
C.
LSI Logic
LSI Logic was a semiconductor company best known for designing and manufacturing custom and standard integrated circuits, particularly ASICs and storage-related chips, for computing and communications markets.
-
D.
DSI
DSI is the Deutsches SOFIA Institut, a German research institute dedicated to supporting and conducting astronomical observations with the SOFIA airborne observatory.
-
E.
DSI
DSI is the IATA airport code for Destin Executive Airport, a public airport serving Destin, Florida.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e51c7c188190b926f3a2a7b5f881 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e656c9e7348190a569a40bd1fca6ba |
completed | April 20, 2026, 4:39 p.m. |
Created at: April 10, 2026, 1:50 p.m.