Triple
T11930628
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | BMP-2 |
E283899
|
entity |
| Predicate | firingPortsLocation |
P35739
|
FINISHED |
| Object | sides of troop compartment |
—
|
LITERAL 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: sides of troop compartment | Statement: [BMP-2, firingPortsLocation, sides of troop compartment]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firingPortsLocation Context triple: [BMP-2, firingPortsLocation, sides of troop compartment]
-
A.
portLocation
chosen
Indicates that a port is geographically situated at or associated with a specific location.
-
B.
servedPorts
Indicates that a network service or device makes specific ports available to accept incoming connections or traffic.
-
C.
firingPlatform
Indicates a platform or structure from which a weapon or projectile is launched or fired.
-
D.
registeredPort
Indicates that a specific network port number has been officially assigned and recorded for use by a particular service or protocol.
-
E.
hasPorts
Indicates that an entity is equipped with or provides access points (ports) for connection, communication, or interface with other entities or systems.
- F. None of above.
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. |
| PD | Predicate disambiguation | batch_69d8bb3af0188190bfb22be5c97b3349 |
completed | April 10, 2026, 8:56 a.m. |
Created at: April 8, 2026, 9:45 p.m.