Triple
T10474287
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Phnom Penh International Airport |
E247004
|
entity |
| Predicate | hasCode |
P9567
|
FINISHED |
| Object | VDPP |
E864715
|
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: VDPP | Statement: [Phnom Penh International Airport, hasCode, VDPP]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: VDPP Context triple: [Phnom Penh International Airport, hasCode, VDPP]
-
A.
VDPP
chosen
VDPP is the ICAO airport code for Phnom Penh International Airport, the main international gateway to Cambodia’s capital city.
-
B.
VDV
VDV is the elite airborne branch of Russia’s armed forces, known for rapid-deployment paratrooper and air-assault operations.
-
C.
DVP
DVP is the National Rail station code for Dover Priory railway station in Dover, Kent, England.
-
D.
DPP
DPP (Device Provisioning Protocol) is a Wi‑Fi Alliance standard that simplifies and secures the process of adding new devices to a Wi‑Fi network without requiring traditional passwords.
-
E.
DPP
DPP is the Maryland state agency responsible for supervising individuals on parole and probation and supporting their reintegration into the 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_69d381c16c248190a2fe5b471e584e9c |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d5094e74048190a2c70ef32c50ba71 |
completed | April 7, 2026, 1:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d8dc68b49481909715c36a4c0e7c4f |
completed | April 10, 2026, 11:18 a.m. |
Created at: April 6, 2026, 12:21 p.m.