Triple
T17417394
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | AV1 |
E423521
|
entity |
| Predicate | competesWith |
P1375
|
FINISHED |
| Object | VVC |
—
|
NE NERFINISHED |
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: VVC | Statement: [AV1, competesWith, VVC]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: VVC Context triple: [AV1, competesWith, VVC]
-
A.
VVC
chosen
VVC (Versatile Video Coding) is a next-generation video compression standard designed to significantly improve coding efficiency over its predecessors for a wide range of applications and resolutions.
-
B.
VVCX
VVCX is a former ICAO airport code that was once assigned to Cat Bi International Airport in Hai Phong, Vietnam.
-
C.
VVI
VVI is the IATA airport code for Viru Viru International Airport, the main international gateway serving Santa Cruz de la Sierra, Bolivia.
-
D.
VRE
VRE is a commuter rail service that operates in Northern Virginia and the Washington, D.C. metropolitan area, providing weekday passenger trains primarily for suburban commuters.
-
E.
VV
VV is the common abbreviation for VistaVision, a high-resolution widescreen 35mm motion picture film format developed by Paramount Pictures in the 1950s.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d889d7d27c819088486ce3f0627fa1 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e44233c7888190a4d2aa703b206851 |
completed | April 19, 2026, 2:47 a.m. |
Created at: April 10, 2026, 5:46 a.m.