Triple
T7900879
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Provo Municipal Airport |
E183448
|
entity |
| Predicate | FAAcode |
P420
|
FINISHED |
| Object | PVU |
E700448
|
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: PVU | Statement: [Provo Municipal Airport, FAAcode, PVU]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: PVU Context triple: [Provo Municipal Airport, FAAcode, PVU]
-
A.
PVU
chosen
PVU is the IATA airport code for Provo Municipal Airport, a public airport serving Provo, Utah.
-
B.
UPVD
UPVD is the commonly used acronym for the University of Perpignan Via Domitia, a French public university located in Perpignan.
-
C.
PV
PV is the post-nominal abbreviation used to denote recipients of the Padma Vibhushan, one of India’s highest civilian honors.
-
D.
UniPV
UniPV is the commonly used abbreviation for the University of Pavia, one of Italy’s oldest and most prestigious universities.
-
E.
pvcs
pvcs is a software version control and configuration management system used to track and manage changes to source code and related files.
- 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_69ca828d13088190b222be7aa9f9315c |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb3a3f4c2c81909ae70b0acf4729be |
completed | March 31, 2026, 3:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cbdfd2dbbc8190b7b1e45b7f0b7515 |
completed | March 31, 2026, 2:53 p.m. |
Created at: March 30, 2026, 5:02 p.m.