Triple
T9050259
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tan Son Nhat International Airport |
E216864
|
entity |
| Predicate | ICAO code |
P419
|
FINISHED |
| Object | VVTS |
E216864
|
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: VVTS | Statement: [Tan Son Nhat International Airport, ICAO code, VVTS]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: VVTS Context triple: [Tan Son Nhat International Airport, ICAO code, VVTS]
-
A.
VVTS
chosen
VVTS is the ICAO airport code for Tan Son Nhat International Airport, the main international gateway serving Ho Chi Minh City, Vietnam.
-
B.
VTSS
VTSS is the ICAO airport code assigned to Hat Yai International Airport in southern Thailand.
-
C.
VTSP
VTSP is the ICAO airport code for Phuket International Airport, a major international gateway to the island of Phuket in Thailand.
-
D.
VES
VES is an abbreviation for the Virtual Execution System, a runtime environment designed to execute managed code in a platform-independent manner.
-
E.
VTST
VTST is the station code for the Vermont/Sunset station on the Los Angeles Metro Rail system.
- 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_69ca83d362e88190ae44b4e4dc194209 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc6b52cc1881909fb011d9a8af2e18 |
completed | April 1, 2026, 12:48 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cffdbd54848190ba79d873321f4fc9 |
completed | April 3, 2026, 5:49 p.m. |
Created at: March 30, 2026, 7:10 p.m.