Triple
T22712335
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cannone da 75/27 modello 06 |
E561633
|
entity |
| Predicate | hasApproximateServiceEntry |
P118961
|
FINISHED |
| Object | circa 1906 |
—
|
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: circa 1906 | Statement: [Cannone da 75/27 modello 06, hasApproximateServiceEntry, circa 1906]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasApproximateServiceEntry Context triple: [Cannone da 75/27 modello 06, hasApproximateServiceEntry, circa 1906]
-
A.
serviceEntryApproximate
chosen
Indicates that the recorded details of a service entry (such as time, duration, or specifics of the service) are estimated rather than exact.
-
B.
hasServiceTo
Indicates that one entity provides, offers, or operates a service for or directed toward another entity.
-
C.
serviceEntryWith
Indicates that one entity is associated with or accompanied by a particular service entry in a joint or linked context.
-
D.
hasFormerService
Indicates that an entity previously provided a service to another entity but no longer does so.
-
E.
hasControlService
Indicates that one entity provides or performs a control-related service for another 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_69e2454f1348819088d83f420925a5c1 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1790998fc8190962e21a28dd08d29 |
completed | April 29, 2026, 3:20 a.m. |
| PD | Predicate disambiguation | batch_69ee62bd657c81909f7b01245b080a5f |
completed | April 26, 2026, 7:08 p.m. |
Created at: April 17, 2026, 3:18 p.m.