Triple
T27998523
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gioia del Colle Air Base |
E707080
|
entity |
| Predicate | usedByDuringConflict |
P176299
|
FINISHED |
| Object | Royal Air Force |
—
|
NE NERFINISHED |
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: Royal Air Force | Statement: [Gioia del Colle Air Base, usedByDuringConflict, Royal Air Force]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedByDuringConflict Context triple: [Gioia del Colle Air Base, usedByDuringConflict, Royal Air Force]
-
A.
usedInConflictType
Indicates that something (such as a resource, method, or capability) is employed or applied within a specific type or category of conflict.
-
B.
usedInConflictPhase
Indicates that an action, resource, or strategy is employed during a specific phase or stage of a conflict.
-
C.
conflictUse
Indicates a relationship where one entity’s use, application, or operation is incompatible with, obstructs, or negatively interferes with another entity’s use.
-
D.
implementedDuringConflict
Indicates that an action, policy, or measure was carried out while an active conflict or war was ongoing.
-
E.
existedDuringConflict
Indicates that an entity was present or active for some or all of the duration of a specified conflict.
- 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_69ef96b980d88190a753b2f9a978595a |
completed | April 27, 2026, 5:02 p.m. |
| NER | Named-entity recognition | batch_69f6dfcafd0c81908d86662948c539d6 |
completed | May 3, 2026, 5:40 a.m. |
| PD | Predicate disambiguation | batch_69f6de07836481908785cde9c511920b |
completed | May 3, 2026, 5:32 a.m. |
| PDg | Predicate description generation | batch_69f6df418f488190a5e7ff41f32dceda |
completed | May 3, 2026, 5:38 a.m. |
Created at: April 27, 2026, 7:55 p.m.