Triple
T18736373
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shepherd Field Air National Guard Base |
E458173
|
entity |
| Predicate | hasICAOCode |
P419
|
FINISHED |
| Object | KMRB |
E951868
|
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: KMRB | Statement: [Shepherd Field Air National Guard Base, hasICAOCode, KMRB]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: KMRB Context triple: [Shepherd Field Air National Guard Base, hasICAOCode, KMRB]
-
A.
KMRB
chosen
KMRB is the ICAO code for Eastern West Virginia Regional Airport, a public airport serving the Martinsburg, West Virginia area.
-
B.
KMRH
KMRH is the ICAO airport code for Michael J. Smith Field, a public airport serving Morehead City in North Carolina, United States.
-
C.
KRM
KRM is the station code for Remagen railway station in Germany.
-
D.
KMHR
KMHR is the ICAO airport code for Mather Airport, a public airport located near Sacramento, California.
-
E.
KMar
KMar is the abbreviated name for the Royal Netherlands Marechaussee, a Dutch gendarmerie force responsible for military police duties, border security, and various national security tasks.
- 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_69d8d394dc308190b6725073f5db324c |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e57689fa508190ad821d361cba9edf |
completed | April 20, 2026, 12:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a05325fae0c8190a7f1a726ad86e3b6 |
completed | May 14, 2026, 2:24 a.m. |
Created at: April 10, 2026, 11:51 a.m.