Triple
T14555904
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MQT |
E341539
|
entity |
| Predicate | ICAOCode |
P419
|
FINISHED |
| Object | KSAW |
E341540
|
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: KSAW | Statement: [MQT, ICAOCode, KSAW]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: KSAW Context triple: [MQT, ICAOCode, KSAW]
-
A.
KSAW
chosen
KSAW is the ICAO airport code for Sawyer International Airport, a public airport serving the Marquette, Michigan area in the United States.
-
B.
KSAV
KSAV is the ICAO airport code for Savannah/Hilton Head International Airport, a commercial and military airfield serving the Savannah, Georgia and Hilton Head Island, South Carolina region.
-
C.
KSAF
KSAF is the ICAO airport code for Santa Fe Regional Airport, a public airport serving Santa Fe, New Mexico.
-
D.
SAAWK
SAAWK is the abbreviation for the Suid-Afrikaanse Akademie vir Wetenskap en Kuns, a South African academy dedicated to promoting Afrikaans language, science, and the arts.
-
E.
KSAU
KSAU is the campus radio station serving Stephen F. Austin State University and the surrounding Nacogdoches, Texas community.
- 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_69d822db9c8481908213ceb39585f792 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb2f1490881908673f429e5288c86 |
completed | April 14, 2026, 9:34 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd8abde0308190819da6867e703ea7 |
completed | May 8, 2026, 7:03 a.m. |
Created at: April 10, 2026, 1:23 a.m.