Triple
T11930642
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | BMP-2 |
E283899
|
entity |
| Predicate | notableVariant |
P4680
|
FINISHED |
| Object | BMP-2D |
E283899
|
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: BMP-2D | Statement: [BMP-2, notableVariant, BMP-2D]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: BMP-2D Context triple: [BMP-2, notableVariant, BMP-2D]
-
A.
BMP-1
The BMP-1 is a Soviet-era tracked infantry fighting vehicle introduced in the 1960s, notable for being one of the first mass-produced IFVs combining troop transport with significant onboard firepower.
-
B.
BMP-2 infantry fighting vehicle
chosen
The BMP-2 infantry fighting vehicle is a Soviet-era tracked armored combat vehicle designed to transport infantry into battle while providing significant firepower and protection on the modern battlefield.
-
C.
BMP
BMP is the Basic Multilingual Plane of Unicode, the primary block of code points that encodes the most commonly used characters from modern and many historic writing systems.
-
D.
BMP
BMP is a simple, uncompressed raster image file format commonly used on Windows systems for storing bitmap graphics.
-
E.
BPS-21
BPS-21 is a senior civil service pay grade in Pakistan typically held by high-ranking government officers such as directors general and equivalent posts.
- 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_69d6ab2ce9c48190b5d39511b524f666 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d90303a9a88190a4044e6310ba9b4b |
completed | April 10, 2026, 2:02 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f458a576fc8190b68b27365cd53caf |
completed | May 1, 2026, 7:39 a.m. |
Created at: April 8, 2026, 9:45 p.m.