Triple
T9820367
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vickers Warwick |
E238513
|
entity |
| Predicate | specialEquipment |
P2728
|
FINISHED |
| Object | airborne lifeboat |
—
|
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: airborne lifeboat | Statement: [Vickers Warwick, specialEquipment, airborne lifeboat]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: specialEquipment Context triple: [Vickers Warwick, specialEquipment, airborne lifeboat]
-
A.
missionEquipment
Indicates that certain equipment is assigned to, used for, or associated with carrying out a specific mission.
-
B.
equippedFor
Indicates that one entity is suitably provided with the necessary tools, features, or capabilities to perform a particular function or handle a specific situation for another entity or purpose.
-
C.
laterEquipment
Indicates that one piece of equipment occurs, is installed, or is used at a later time than another piece of equipment.
-
D.
usesEquipment
chosen
Indicates that an entity employs or operates a particular piece of equipment to perform an action or fulfill a function.
-
E.
recommendedEquipment
Indicates that one entity suggests or endorses another entity as suitable equipment to be used in a particular context or activity.
- 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_69ca84dfde1481909f47c286d715f892 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdb313134081908eb0ba3a22b22e2b |
completed | April 2, 2026, 12:06 a.m. |
| PD | Predicate disambiguation | batch_69cd03e01ea881909a7d93fc3994ace5 |
completed | April 1, 2026, 11:39 a.m. |
Created at: March 30, 2026, 8:31 p.m.