Triple
T16353181
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | AS-90 turret |
E397107
|
entity |
| Predicate | supportsFiringMode |
P9011
|
FINISHED |
| Object | indirect fire |
—
|
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: indirect fire | Statement: [AS-90 turret, supportsFiringMode, indirect fire]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsFiringMode Context triple: [AS-90 turret, supportsFiringMode, indirect fire]
-
A.
supportedMode
Indicates that a system, device, or component is capable of operating in or handling a particular mode.
-
B.
fireModes
chosen
Indicates the different ways or settings in which a weapon or device can be fired or operated.
-
C.
availableInMode
Indicates that something can be used, accessed, or functions within a specified mode or operational setting.
-
D.
supportsObservationModes
Indicates that one entity provides or is compatible with specific modes or methods of observation used by another entity.
-
E.
supportsBurstMode
Indicates that an entity is capable of operating in a burst mode, handling short periods of intensified or rapid activity beyond its normal continuous capacity.
- 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_69d87f26864c819088365ca381a003c2 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e2faccab748190b11e0808e422f2ea |
completed | April 18, 2026, 3:30 a.m. |
| PD | Predicate disambiguation | batch_69e226f37ecc819082af58b29b4e39d1 |
completed | April 17, 2026, 12:26 p.m. |
Created at: April 10, 2026, 5:07 a.m.