Triple
T28480435
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | French Army special forces |
E720675
|
entity |
| Predicate | typicalInsertionMethods |
P202680
|
FINISHED |
| Object | parachute insertion |
—
|
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: parachute insertion | Statement: [French Army special forces, typicalInsertionMethods, parachute insertion]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalInsertionMethods Context triple: [French Army special forces, typicalInsertionMethods, parachute insertion]
-
A.
insertionManeuver
Indicates the action of placing or guiding one object or component into another or into a designated position.
-
B.
insertedUnder
Indicates that one entity has been placed or positioned beneath another entity, typically in a physical or structural context.
-
C.
accessionMethod
Indicates the process or means by which something is acquired, obtained, or added to a collection or system.
-
D.
typicalInstallMethod
Indicates the usual or most common method by which something is installed or set up.
-
E.
typicalInterface
Indicates that one entity serves as the standard or commonly used interface through which another entity is accessed or interacted with.
- 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_69f01a5983f48190b7c1b8857245a4f7 |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_6a00acf86e4081909aad9356650e0f79 |
completed | May 10, 2026, 4:06 p.m. |
| PD | Predicate disambiguation | batch_6a00ac813fd08190a0a7782609e74e70 |
completed | May 10, 2026, 4:04 p.m. |
| PDg | Predicate description generation | batch_6a00acf7923c819091ae7fbda05164f6 |
completed | May 10, 2026, 4:06 p.m. |
Created at: April 28, 2026, 2:55 a.m.