Triple
T30126891
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Repression of War Experience |
E765719
|
entity |
| Predicate | hasAuthorMilitaryService |
P180533
|
FINISHED |
| Object | British Army in World War I |
—
|
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: British Army in World War I | Statement: [Repression of War Experience, hasAuthorMilitaryService, British Army in World War I]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAuthorMilitaryService Context triple: [Repression of War Experience, hasAuthorMilitaryService, British Army in World War I]
-
A.
hasMilitaryServiceStart
Indicates the date or point in time when an entity’s period of military service began.
-
B.
hasMilitaryStatus
Indicates that an entity possesses a specific military affiliation, role, or status (such as active duty, reserve, or veteran).
-
C.
hadMilitaryServiceFrom
Indicates that an entity performed or was engaged in military service starting from a specified point in time.
-
D.
stanceOnMilitaryService
Indicates an entity’s expressed position, attitude, or policy regarding military service.
-
E.
involvesMilitaryService
Indicates that the relationship or situation includes participation in, obligation to, or association with formal military service.
- 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_69f22477d1a081908df2b7e6ed16859d |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f7431c0eec81909ead443e07d75e18 |
completed | May 3, 2026, 12:44 p.m. |
| PD | Predicate disambiguation | batch_69f74143cf708190a12d487884298437 |
completed | May 3, 2026, 12:36 p.m. |
| PDg | Predicate description generation | batch_69f7431aac148190bb6aac59817c174a |
completed | May 3, 2026, 12:44 p.m. |
Created at: April 29, 2026, 7:14 p.m.