Triple
T7501212
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tirana International Airport |
E177263
|
entity |
| Predicate | ICAO code |
P419
|
FINISHED |
| Object | LATI |
E668650
|
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: LATI | Statement: [Tirana International Airport, ICAO code, LATI]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: LATI Context triple: [Tirana International Airport, ICAO code, LATI]
-
A.
LATI
chosen
LATI is the ICAO airport code for Tirana International Airport Nënë Tereza, the main international gateway to Albania.
-
B.
LAT
LAT is the International Ice Hockey Federation (IIHF) country code used to represent the Latvia men's national ice hockey team in international competitions.
-
C.
LAT
LAT is the Large Area Telescope, a high-energy gamma-ray detector aboard NASA's Fermi Gamma-ray Space Telescope used to study cosmic gamma-ray sources.
-
D.
LAC
LAC refers to the Los Angeles Clippers, a professional NBA basketball team based in Los Angeles and a crosstown rival of the Los Angeles Lakers.
-
E.
LAJ
LAJ is the station code for La Junta station, an Amtrak railroad stop in La Junta, Colorado, serving long-distance passenger trains.
- 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_69c69f2696688190915a8458f2398211 |
completed | March 27, 2026, 3:15 p.m. |
| NER | Named-entity recognition | batch_69c6f59aabb8819085bdbe9c793d5b8b |
completed | March 27, 2026, 9:24 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c84608021481908ce58a131d75188b |
completed | March 28, 2026, 9:20 p.m. |
Created at: March 27, 2026, 3:44 p.m.