Triple
T17109329
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | T-44 medium tank |
E415182
|
entity |
| Predicate | turretPosition |
P11887
|
FINISHED |
| Object | more centrally mounted turret |
—
|
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: more centrally mounted turret | Statement: [T-44 medium tank, turretPosition, more centrally mounted turret]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: turretPosition Context triple: [T-44 medium tank, turretPosition, more centrally mounted turret]
-
A.
turretOrigin
Indicates the original source, base, or starting point from which a turret is derived, mounted, or deployed.
-
B.
turretPlacement
chosen
Indicates the spatial or positional relationship defining where a turret is placed relative to its environment or reference objects.
-
C.
turret
Indicates that an entity is equipped with or associated with a turret, typically a rotating weapon or defense mechanism.
-
D.
turretBasedOn
Indicates that one turret is derived from, modeled after, or constructed using the design or components of another turret.
-
E.
positionRelativeToTower
Indicates the spatial relationship or placement of an entity with respect to a specified tower.
- 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_69d886d090cc8190a39cb94992586905 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3dc29c884819092a97d9663a1b1f7 |
completed | April 18, 2026, 7:31 p.m. |
| PD | Predicate disambiguation | batch_69e35d6b1b988190a8d6b6fe78c35e59 |
completed | April 18, 2026, 10:31 a.m. |
Created at: April 10, 2026, 5:35 a.m.