Triple
T406087
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Special Air Service |
E9386
|
entity |
| Predicate | selectionFeature |
P136
|
FINISHED |
| Object | extremely demanding selection process |
—
|
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: extremely demanding selection process | Statement: [Special Air Service, selectionFeature, extremely demanding selection process]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: selectionFeature Context triple: [Special Air Service, selectionFeature, extremely demanding selection process]
-
A.
selectionMadeBy
Indicates that a particular choice or selection was performed or decided by a specific agent or entity.
-
B.
selectionCriteria
chosen
Indicates the conditions or rules used to choose certain entities from a larger set.
-
C.
selectedTo
Indicates that one entity has been chosen or designated from a set of candidates to perform a role, receive something, or participate in an activity in relation to another entity.
-
D.
selectFire
Indicates choosing or designating a specific fire source, mode, or target for use or activation.
-
E.
featureType
Indicates the specific kind or category of feature that characterizes or distinguishes an entity.
- 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_69a2e8004cb88190b92ed1add6abf41a |
completed | Feb. 28, 2026, 1:05 p.m. |
| NER | Named-entity recognition | batch_69a2ecbc00508190bbb602179273f29c |
completed | Feb. 28, 2026, 1:25 p.m. |
| PD | Predicate disambiguation | batch_69a2e971a3a481909e6b075f25dd234a |
completed | Feb. 28, 2026, 1:11 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.