Triple
T1537189
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Minneapolis–Saint Paul International Airport |
E32578
|
entity |
| Predicate | FAAcode |
P420
|
FINISHED |
| Object | MSP |
E176562
|
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: MSP | Statement: [Minneapolis–Saint Paul International Airport, FAAcode, MSP]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MSP Context triple: [Minneapolis–Saint Paul International Airport, FAAcode, MSP]
-
A.
MSP
MSP is the primary statewide law enforcement agency responsible for highway patrol, criminal investigations, and public safety across the Commonwealth of Massachusetts.
-
B.
MSP
MSP stands for Member of the Scottish Parliament, an elected representative in Scotland's devolved legislature.
-
C.
MSP
MSP is the primary statewide law enforcement agency responsible for highway patrol, criminal investigations, and public safety in Maryland.
-
D.
MSP
chosen
MSP is the primary international airport serving the Minneapolis–Saint Paul metropolitan area in Minnesota, USA.
-
E.
MPS
MPS is a leading German research institute specializing in the study of the Sun and the solar system, operating under the Max Planck Society.
- 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_69a885ea86308190998f6bc14bb91f8e |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a9082af6d88190b63a187ef516bb21 |
completed | March 5, 2026, 4:35 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad3706935481909455528b1bc4ce6c |
completed | March 8, 2026, 8:44 a.m. |
Created at: March 4, 2026, 7:26 p.m.