Triple
T15147013
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Caselle Torinese |
E361835
|
entity |
| Predicate | airportICAO |
P419
|
FINISHED |
| Object | LIMF |
E361834
|
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: LIMF | Statement: [Caselle Torinese, airportICAO, LIMF]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: LIMF Context triple: [Caselle Torinese, airportICAO, LIMF]
-
A.
LIMF
chosen
LIMF is the ICAO airport code for Turin Airport, an international airport serving the city of Turin in northern Italy.
-
B.
LIM
LIM is the IATA airport code for Jorge Chávez International Airport, the main international gateway serving Lima, Peru.
-
C.
LIMJ
LIMJ is the ICAO airport code for Genoa Cristoforo Colombo Airport, the main international airport serving the city of Genoa in Italy.
-
D.
LIMC
LIMC is the ICAO airport code for Milan Malpensa Airport, a major international airport serving the Milan metropolitan area in Italy.
-
E.
LIF
LIF is the vehicle registration code for the town and district of Lichtenfels in the German state of Bavaria.
- 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_69d85a0759908190b8a051d2e2a1cbe6 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e005c825a481909d00098b0e743365 |
completed | April 15, 2026, 9:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fed323e5548190902f65db50a36cd4 |
completed | May 9, 2026, 6:24 a.m. |
Created at: April 10, 2026, 3:07 a.m.