Triple
T18376262
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Columbus Airport (Georgia) |
E446322
|
entity |
| Predicate | FAAcode |
P420
|
FINISHED |
| Object | CSG |
—
|
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: CSG | Statement: [Columbus Airport (Georgia), FAAcode, CSG]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: CSG Context triple: [Columbus Airport (Georgia), FAAcode, CSG]
-
A.
CSG
CSG is the commonly used abbreviation for the Guiana Space Centre, a major European spaceport located in French Guiana.
-
B.
CSG
chosen
CSG is the IATA airport code for Columbus Airport, a regional airport serving Columbus, Georgia, in the United States.
-
C.
CSG
CSG is the Commercial Stakeholder Group, a body representing commercial and business interests within the Internet Corporation for Assigned Names and Numbers (ICANN) policy development process.
-
D.
FS CSG
FS CSG is the station code used by the Italian railway network to identify Como San Giovanni railway station.
-
E.
CSM
CSM is the enigmatic primary antagonist in the television series "The X-Files," known for his deep involvement in government conspiracies and the alien cover-up.
- 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_69d8b9f370b88190b1e5081c2c238e7f |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e51759353481908aa2de599fd2cf3b |
completed | April 19, 2026, 5:56 p.m. |
Created at: April 10, 2026, 10:45 a.m.