Triple
T3681668
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ghost Division |
E78125
|
entity |
| Predicate | componentForces |
P50280
|
FINISHED |
| Object | tanks |
—
|
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: tanks | Statement: [Ghost Division, componentForces, tanks]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: componentForces Context triple: [Ghost Division, componentForces, tanks]
-
A.
axisForces
Indicates a relationship where one entity exerts or applies force along, around, or with respect to a particular axis defined by another entity.
-
B.
includedForcesFrom
Indicates that one set of forces is derived from, or incorporated within, another set of forces.
-
C.
nativeForces
Indicates that certain forces or troops are indigenous to, or originate from, a particular place, group, or population.
-
D.
primaryForces
Indicates a relationship where one or more forces are identified as the main or dominant contributors to an effect, behavior, or outcome among all forces involved.
-
E.
inForceIn
Indicates that a rule, law, agreement, or condition is currently valid and operative within a specified jurisdiction, context, or time frame.
- F. None of above. chosen
Provenance (4 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_69ad85e18c1c8190be8aafb227f39f48 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc492aed481909e8986378ad283fc |
completed | March 8, 2026, 6:48 p.m. |
| PD | Predicate disambiguation | batch_69adb84be1fc81909721c871babb4633 |
completed | March 8, 2026, 5:56 p.m. |
| PDg | Predicate description generation | batch_69adb97cdb788190a5ce96b21bd157ab |
completed | March 8, 2026, 6:01 p.m. |
Created at: March 8, 2026, 3:25 p.m.