Triple
T16936262
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Antalya Airport |
E410833
|
entity |
| Predicate | ICAO code |
P419
|
FINISHED |
| Object | LTAI |
E410833
|
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: LTAI | Statement: [Antalya Airport, ICAO code, LTAI]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: LTAI Context triple: [Antalya Airport, ICAO code, LTAI]
-
A.
LTAI
chosen
LTAI is the ICAO airport code for Antalya Airport, a major international gateway serving the city of Antalya and Turkey’s Mediterranean tourism region.
-
B.
LAI
LAI is the vehicle registration code assigned to the Finnish town of Laitila.
-
C.
LTAU
LTAU is the ICAO airport code for Kayseri Erkilet Airport, a civil-military airport serving the city of Kayseri in central Turkey.
-
D.
LTAZ
LTAZ is the ICAO airport code for Nevşehir Kapadokya Airport, which serves the Cappadocia region of central Turkey.
-
E.
LRTA
LRTA is the public transportation agency that operates bus and paratransit services in Lowell, Massachusetts and surrounding communities.
- 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_69d886c886688190967be07322597ac9 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3cf2a05f48190a0a8ac86985f4000 |
completed | April 18, 2026, 6:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00cfe2d4f48190b965b6c0a3cc0125 |
completed | May 10, 2026, 6:35 p.m. |
Created at: April 10, 2026, 5:30 a.m.