Triple
T18298366
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Friends' Ambulance Unit |
E438291
|
entity |
| Predicate | providedServicesTo |
P59424
|
FINISHED |
| Object | military casualties |
—
|
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: military casualties | Statement: [Friends' Ambulance Unit, providedServicesTo, military casualties]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: providedServicesTo Context triple: [Friends' Ambulance Unit, providedServicesTo, military casualties]
-
A.
providesServices
chosen
Indicates that one entity supplies or performs services for the benefit or use of another entity.
-
B.
offeredService
Indicates that one entity has provided or made available a service to another entity.
-
C.
serviceFor
Indicates that one entity provides a service or performs functions on behalf of another entity.
-
D.
providesServiceTowards
Indicates that one entity delivers or performs a service directed to or for the benefit of another entity.
-
E.
publicServices
Indicates that one entity provides or is associated with services offered collectively for the benefit of the general public.
- 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_69d8b915e3e881909125d760c15d0c29 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e5017d96588190ac1e326803142976 |
completed | April 19, 2026, 4:23 p.m. |
| PD | Predicate disambiguation | batch_69e44fdf43d08190bbcfb6b1fe3cc0ee |
completed | April 19, 2026, 3:45 a.m. |
Created at: April 10, 2026, 10:35 a.m.