Triple
T14453030
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | VASU |
E358383
|
entity |
| Predicate | hasIcaoCode |
P419
|
FINISHED |
| Object | VASU |
E358383
|
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: VASU | Statement: [VASU, hasIcaoCode, VASU]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: VASU Context triple: [VASU, hasIcaoCode, VASU]
-
A.
VASU
chosen
VASU is the ICAO airport code for Surat Airport, a domestic airport serving the city of Surat in the Indian state of Gujarat.
-
B.
VASS
VASS is Vietnam’s leading national research institution dedicated to the study and development of the social sciences.
-
C.
VASCO
VASCO is a regional airline in Vietnam that operates domestic flights, often serving smaller airports and routes on behalf of Vietnam Airlines.
-
D.
VSH
VSH is the Indian Railways station code for Vashi railway station, a key suburban rail stop in Navi Mumbai, Maharashtra.
-
E.
VG AS
VG AS is a Norwegian media company best known for publishing Verdens Gang (VG), one of Norway’s largest and most influential newspapers and news websites.
- 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_69d82794dfa081909b9134ad2e32244b |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de916244948190bb09d1bfc485ba50 |
completed | April 14, 2026, 7:11 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd5be12da481909b11290965ec48da |
completed | May 8, 2026, 3:43 a.m. |
Created at: April 10, 2026, 1:19 a.m.