Triple
T11403135
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Montrose Regional Airport |
E270165
|
entity |
| Predicate | FAAcode |
P420
|
FINISHED |
| Object | MTJ |
E923835
|
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: MTJ | Statement: [Montrose Regional Airport, FAAcode, MTJ]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MTJ Context triple: [Montrose Regional Airport, FAAcode, MTJ]
-
A.
MTJ
MTJ is the railway station code for Mathura Junction, a major rail hub in the Indian state of Uttar Pradesh.
-
B.
MTJ
chosen
MTJ is the IATA airport code for Montrose Regional Airport, a commercial airport serving the Montrose and Telluride areas in western Colorado, USA.
-
C.
MJT
MJT is the IATA airport code for Mytilene International Airport on the Greek island of Lesbos.
-
D.
MTM
MTM is the company responsible for operating Melbourne’s metropolitan passenger rail network in Victoria, Australia.
-
E.
MTM
MTM is the Mercury Transfer Module of the BepiColombo mission, responsible for propelling and guiding the spacecraft on its journey to Mercury.
- 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_69d6aaddeaa8819088b30ef7b50598c9 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8014ab46881909fa1d425926c617b |
completed | April 9, 2026, 7:43 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e5b834cee48190ac09c1e1df4c12d0 |
completed | April 20, 2026, 5:23 a.m. |
Created at: April 8, 2026, 9:34 p.m.