Triple
T9218640
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2nd Cavalry Group |
E221303
|
entity |
| Predicate | supportedFormationType |
P86919
|
FINISHED |
| Object | armored formations |
—
|
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: armored formations | Statement: [2nd Cavalry Group, supportedFormationType, armored formations]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportedFormationType Context triple: [2nd Cavalry Group, supportedFormationType, armored formations]
-
A.
supportedFormation
Indicates that one entity provided assistance, resources, or conditions that enabled the creation or establishment of another entity or structure.
-
B.
supportsForm
Indicates that one entity provides compatibility or backing for a particular form, format, or type associated with another entity.
-
C.
containsFormation
Indicates that one entity spatially or structurally includes or encloses a formation as part of its extent or composition.
-
D.
supportsForms
Indicates that one entity is capable of handling, accepting, or working with specific forms or form types associated with another entity.
-
E.
onFormation
Indicates that one entity is located on or attached to the surface of a formation (such as a geological or structural feature).
- 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_69ca83eae42c8190a0ea9e040710a277 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69ccda730f688190b64b2cc8c4898ac3 |
completed | April 1, 2026, 8:42 a.m. |
| PD | Predicate disambiguation | batch_69cc660ce23c81909c7bbe10f4a05f36 |
completed | April 1, 2026, 12:25 a.m. |
| PDg | Predicate description generation | batch_69cc687067fc81909da2d78fda0cdcfb |
completed | April 1, 2026, 12:36 a.m. |
Created at: March 30, 2026, 7:27 p.m.