Triple
T1703871
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sirmium |
E36825
|
entity |
| Predicate | hadInfrastructure |
P2560
|
FINISHED |
| Object | imperial palace |
—
|
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: imperial palace | Statement: [Sirmium, hadInfrastructure, imperial palace]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hadInfrastructure Context triple: [Sirmium, hadInfrastructure, imperial palace]
-
A.
usesInfrastructure
Indicates that one entity makes use of, depends on, or operates through the infrastructure provided or managed by another entity.
-
B.
hasInfrastructureType
chosen
Indicates that an entity possesses or is associated with a specific category or type of infrastructure.
-
C.
hasGlobalInfrastructure
Indicates that an entity possesses infrastructure, facilities, or operational capabilities that are distributed across multiple countries or regions worldwide.
-
D.
parallelInfrastructure
Indicates that two or more infrastructure elements are arranged or operate in parallel to each other, typically serving similar functions simultaneously.
-
E.
hadFort
Indicates that an entity possessed, controlled, or contained a fort at some time.
- 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_69a88617439c819094ffb5d16a0f6307 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69ab75ad24408190814069e6e3ef9e59 |
completed | March 7, 2026, 12:47 a.m. |
| PD | Predicate disambiguation | batch_69aa61bad17c8190861b92cfb423f68f |
completed | March 6, 2026, 5:10 a.m. |
Created at: March 4, 2026, 7:30 p.m.